{"schemaVersion":"jobsearcher.job.v1","id":"02efca7e0cd6041f4d832c72","url":"https://jobsearcher.com/jobs/02efca7e0cd6041f4d832c72","canonicalUrl":"https://jobsearcher.com/jobs/02efca7e0cd6041f4d832c72","title":"AI Systems & Platform Internals - Technical Architect","description":"GPU, Kernel & Distributed Performance\r\nAgentic & Multimodal Platform Internals\r\nAccellor is an AI-native services firm purpose-built for the post-ChatGPT era. Free from legacy constraints, we focus on delivering measurable business outcomes through advanced AI, data, and engineering capabilities. Our mission is to operationalize AI at scale and unlock sustained enterprise value.\r\nOur offerings span AI solutions, data services, enterprise applications, and product engineering, tailored to industry-specific needs across healthcare, life sciences, telecom, retail, financial services, and technology. By leveraging design thinking and technology-agnostic architectures, we ensure faster time-to-value and seamless interoperability.\r\nWith a proven track record of enabling Fortune 100 enterprises and global innovators, Accellor stands as a trusted partner for organizations seeking to harness the full potential of AI. Our vision is clear: to build intelligent, connected ecosystems that deliver measurable outcomes and redefine the future of enterprise transformation.\r\nTechnical Architect — AI Systems & Platform Internals Experience: 10-12 Years\r\nRole Type: Technical Architect / Staff-Level Systems Architect\r\nRole Summary Accellor is looking for a Technical Architect — AI Systems, Inference & Platform Internals to help design, scale, and optimize the systems that power ChatGPT, OpenAI API, Codex, agentic systems, multimodal experiences, and internal research workloads.\r\nThis role is focused on the internal AI systems stack, including inference runtime, model serving, GPU infrastructure, distributed systems, context engineering, cost optimization, evaluation gates, observability, release safety, and production reliability.\r\nThe ideal candidate is a senior hands-on architect who can reason across the full AI platform — from GPU-level performance and distributed inference to product-scale reliability, model deployment, safety, and cost-efficient operations.\r\nKey Responsibilities AI Systems Architecture Design and evolve large-scale AI systems that support ChatGPT, OpenAI API, Codex, agentic workflows, multimodal models, and research workloads.\r\nDefine architecture across inference runtime, model serving, request routing, batching, KV-cache handling, GPU scheduling, distributed execution, observability, release gates, and production rollout.\r\nOwn technical trade-offs across latency, throughput, reliability, correctness, safety, scalability, cost, and infrastructure efficiency.\r\nInference Runtime & Model Serving Architect high-throughput, low-latency inference systems across large-scale GPU clusters.\r\nWork across inference engines, serving layers, scheduling systems, caching, streaming, deployment pipelines, and runtime optimization.\r\nPartner with engineering teams to improve model-serving efficiency, tail latency, GPU utilization, memory efficiency, correctness under load, and cost per request.\r\nGuide architecture decisions involving PyTorch, JAX, Triton, vLLM-style serving, CUDA/Triton kernels, distributed inference, tensor parallelism, pipeline parallelism, model sharding, and long-context serving.\r\nGPU, Kernel & Distributed Performance Analyze and improve performance across GPU kernels, memory movement, collective communication, orchestration, and runtime scheduling.\r\nGuide engineering decisions involving CUDA, Triton, NCCL/RCCL, GPU profiling, memory pressure, compute utilization, tensor layouts, interconnect behavior, and distributed execution.\r\nIdentify system-level bottlenecks across compute, memory, networking, scheduling, model execution, and data movement.\r\nContext Engineering Design and guide context engineering frameworks that determine what information should be passed to the model, how it should be structured, how much context should be used, and how context quality should be measured.\r\nOwn architecture patterns for prompt structure, dynamic context assembly, retrieval-augmented generation, long-context management, conversation memory, tool context, agent state, multimodal context, source grounding, permission-aware retrieval, context compression, and context auditability.\r\nEnsure AI systems use the right context, from the right source, with the right permissions, at the right cost, and with measurable quality.\r\nCost Optimization Frameworks Design and build cost optimization frameworks for large-scale LLM and GenAI workloads.\r\nCreate architecture patterns that reduce unnecessary token usage, redundant retrieval, repeated model calls, inefficient inference paths, and avoidable infrastructure spend.\r\nDrive model routing, token budgeting, prompt compression, context pruning, semantic caching, response caching, batch inference, async execution, fallback strategies, and cost telemetry across AI workflows.\r\nEnsure cost optimization does not compromise quality, safety, grounding, reliability, or user experience.\r\nTraining & Research Infrastructure Collaborate with research and training infrastructure teams to support large-scale model training and post-training workflows.\r\nContribute to architecture around distributed training, checkpointing, orchestration, fault tolerance, observability, data movement, evaluation infrastructure, and experiment velocity.\r\nSupport frontier model workflows across pre-training, post-training, reinforcement learning, agent training, evaluation harnesses, and large-scale experiment execution.\r\nRelease Safety, Validation & Evaluation Gates Architect validation and release systems that ensure model updates, inference engine changes, runtime images, prompt changes, context changes, and platform releases are correct, safe, performant, and regression-free.\r\nDefine release gates across correctness, numerical stability, latency, throughput, token usage, cost regression, context quality, retrieval quality, safety behavior, reliability, and model output quality.\r\nEnsure platform optimizations do not reduce safety, grounding, quality, or user trust.\r\nReliability, Observability & Production Operations Design systems that make AI infrastructure observable, debuggable, reliable, and operationally safe.\r\nDefine telemetry, tracing, dashboards, alerts, logs, profiling views, runbooks, SLOs, and post-incident learning loops.\r\nProvide visibility into prompts, context payloads, retrieved sources, token consumption, model selection, cache behavior, inference latency, GPU utilization, evaluation scores, safety events, cost, and failures.\r\nTurn production issues into stronger platform abstractions, safer rollout mechanisms, better automation, and more reliable infrastructure.\r\nAgentic & Multimodal Platform Internals Support architecture for AI agents, tool use, memory, function calling, multimodal interaction, long-running workflows, and internal or external agent deployment.\r\nWork across agent harnesses, evaluation pipelines, workflow orchestration, safety controls, state management, tool execution, memory systems, and product-facing runtime constraints.\r\nEnsure agentic and multimodal systems are reliable, observable, secure, cost-aware, and safe under real workloads.\r\nTechnical Leadership Work closely with Research, Inference, Runtime, Infrastructure, Product, Safety, Security, Technical Success, and Deployment teams.\r\nAct as a senior technical authority who can cut across layers, resolve ambiguity, identify systemic risks, and drive architecture decisions.\r\nMentor engineers and technical leads on distributed systems, performance engineering, context engineering, cost optimization, production readiness, AI platform design, and architecture trade-offs.\r\nRepresent architecture decisions through design docs, RFCs, diagrams, technical reviews, operational plans, and leadership-level summaries.\r\nRequirements Required Qualifications 10-12 years of experience in software engineering, systems architecture, ML infrastructure, distributed systems, platform engineering, inference systems, cloud infrastructure, or large-scale backend engineering\r\nStrong hands-on engineering experience with Python and at least one systems/backend language such as C++, Go, Rust, Java, or TypeScript\r\nDeep understanding of distributed systems, production infrastructure, reliability engineering, scalability, observability, and fault-tolerant architecture\r\nExperience designing or operating large-scale systems involving APIs, microservices, distributed compute, orchestration, job scheduling, caching, high-availability infrastructure, and production monitoring\r\nStrong understanding of AI/ML systems, especially model serving, inference workflows, context engineering, retrieval systems, evaluation pipelines, and production model deployment\r\nPractical understanding of GPU systems, accelerator-based workloads, CUDA/Triton-style programming, distributed inference, GPU profiling, memory optimization, and communication libraries such as NCCL or RCCL\r\nExperience with ML frameworks and serving stacks such as PyTorch, JAX, TensorFlow, Triton, vLLM-style serving, Apache Ray, Kubernetes-based serving, or internal model-serving systems\r\nAbility to debug complex problems across model behavior, runtime systems, distributed infrastructure, networking, GPU execution, context quality, retrieval quality, evaluation harnesses, and production services\r\nStrong communication skills with the ability to write clear architecture documents, evaluate trade-offs, review implementation quality, and align teams around technically sound decisions\r\nPreferred Qualifications Experience working on LLM inference, multimodal inference, agent infrastructure, AI assistants, coding agents, or frontier-model serving platforms\r\nExperience with tensor parallelism, pipeline parallelism, model sharding, KV-cache optimization, batching, speculative decoding, streaming inference, and long-context serving\r\nExperience designing context engineering platforms, prompt/version management systems, model-routing frameworks, semantic caching layers, token-budgeting systems, or LLM cost dashboards\r\nExperience profiling GPU workloads using Nsight Systems, Nsight Compute, rocprof, perf, Prometheus, Grafana, OpenTelemetry, or custom profiling systems\r\nExperience with large-scale distributed training, RL infrastructure, checkpointing, ML compiler optimizations, model graph transformations, or training runtime systems\r\nExperience designing release gates, regression detection systems, canary systems, CI/CD validation frameworks, and production safety controls for performance-sensitive infrastructure\r\nExperience with evals, model quality measurement, hallucination detection, grounding evaluation, safety testing, and model behavior monitoring\r\nTechnical Skill Areas: AI Systems: LLM serving, inference runtime, training infrastructure, post-training workflows, agent systems, multimodal models\r\nInference: batching, routing, KV-cache, streaming, latency optimization, model serving, tensor parallelism, pipeline parallelism\r\nPerformance Engineering: CUDA, Triton, GPU profiling, kernel optimization, memory bandwidth, communication libraries, distributed execution\r\nContext Engineering: prompt architecture, dynamic context assembly, RAG, memory, context compression, context ranking, source grounding, permission-aware retrieval\r\nCost Optimization: token budgeting, caching, model routing, fallback strategies, cost telemetry, batching, async workflows, cost-quality trade-offs\r\nDistributed Systems: scheduling, orchestration, reliability, fault tolerance, observability, scalability, service design\r\nML Frameworks: PyTorch, JAX, TensorFlow, Triton, vLLM-style serving, Ray\r\nInfrastructure: Kubernetes, Docker, Terraform, CI/CD, cloud platforms, Linux systems, networking, storage\r\nSafety & Validation: evals, release gates, canaries, regression testing, model behavior validation, rollout safety\r\nCandidate Profile: The ideal candidate is a senior hands-on architect who can operate across the full AI systems stack.\r\nThey should be able to discuss GPU memory bottlenecks, distributed inference, model-serving reliability, context quality, cost optimization, release validation, eval pipelines, observability, and production rollout with engineering teams, while also explaining architecture decisions clearly to senior leadership.\r\nThe candidate should not be limited to architecture diagrams. They must be capable of reviewing implementation quality, identifying bottlenecks, debugging production issues, challenging weak assumptions, and converting repeated failures into stronger platform abstractions.\r\nThis role requires the judgment of a senior architect, the debugging mindset of a systems engineer, and the ownership mindset required for production AI infrastructure.\r\nJ-18808-Ljbffr","company":"Accellor","rawCompany":"accellor","city":"Mountain View","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-08-12T00:51:01.133Z","occupations":[{"code":"15-1299.08","title":"Computer Systems Engineers/Architects","slug":"computer-systems-engineers-architects"},{"code":"15-1211.00","title":"Computer Systems Analysts","slug":"computer-systems-analysts"},{"code":"15-1243.00","title":"Database Architects","slug":"database-architects"}],"industries":[{"code":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"},{"code":"513210","title":"Software Publishers","slug":"software-publishers"},{"code":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"AI Systems & Platform Internals - Technical Architect","description":"GPU, Kernel & Distributed Performance\r\nAgentic & Multimodal Platform Internals\r\nAccellor is an AI-native services firm purpose-built for the post-ChatGPT era. Free from legacy constraints, we focus on delivering measurable business outcomes through advanced AI, data, and engineering capabilities. Our mission is to operationalize AI at scale and unlock sustained enterprise value.\r\nOur offerings span AI solutions, data services, enterprise applications, and product engineering, tailored to industry-specific needs across healthcare, life sciences, telecom, retail, financial services, and technology. By leveraging design thinking and technology-agnostic architectures, we ensure faster time-to-value and seamless interoperability.\r\nWith a proven track record of enabling Fortune 100 enterprises and global innovators, Accellor stands as a trusted partner for organizations seeking to harness the full potential of AI. Our vision is clear: to build intelligent, connected ecosystems that deliver measurable outcomes and redefine the future of enterprise transformation.\r\nTechnical Architect — AI Systems & Platform Internals Experience: 10-12 Years\r\nRole Type: Technical Architect / Staff-Level Systems Architect\r\nRole Summary Accellor is looking for a Technical Architect — AI Systems, Inference & Platform Internals to help design, scale, and optimize the systems that power ChatGPT, OpenAI API, Codex, agentic systems, multimodal experiences, and internal research workloads.\r\nThis role is focused on the internal AI systems stack, including inference runtime, model serving, GPU infrastructure, distributed systems, context engineering, cost optimization, evaluation gates, observability, release safety, and production reliability.\r\nThe ideal candidate is a senior hands-on architect who can reason across the full AI platform — from GPU-level performance and distributed inference to product-scale reliability, model deployment, safety, and cost-efficient operations.\r\nKey Responsibilities AI Systems Architecture Design and evolve large-scale AI systems that support ChatGPT, OpenAI API, Codex, agentic workflows, multimodal models, and research workloads.\r\nDefine architecture across inference runtime, model serving, request routing, batching, KV-cache handling, GPU scheduling, distributed execution, observability, release gates, and production rollout.\r\nOwn technical trade-offs across latency, throughput, reliability, correctness, safety, scalability, cost, and infrastructure efficiency.\r\nInference Runtime & Model Serving Architect high-throughput, low-latency inference systems across large-scale GPU clusters.\r\nWork across inference engines, serving layers, scheduling systems, caching, streaming, deployment pipelines, and runtime optimization.\r\nPartner with engineering teams to improve model-serving efficiency, tail latency, GPU utilization, memory efficiency, correctness under load, and cost per request.\r\nGuide architecture decisions involving PyTorch, JAX, Triton, vLLM-style serving, CUDA/Triton kernels, distributed inference, tensor parallelism, pipeline parallelism, model sharding, and long-context serving.\r\nGPU, Kernel & Distributed Performance Analyze and improve performance across GPU kernels, memory movement, collective communication, orchestration, and runtime scheduling.\r\nGuide engineering decisions involving CUDA, Triton, NCCL/RCCL, GPU profiling, memory pressure, compute utilization, tensor layouts, interconnect behavior, and distributed execution.\r\nIdentify system-level bottlenecks across compute, memory, networking, scheduling, model execution, and data movement.\r\nContext Engineering Design and guide context engineering frameworks that determine what information should be passed to the model, how it should be structured, how much context should be used, and how context quality should be measured.\r\nOwn architecture patterns for prompt structure, dynamic context assembly, retrieval-augmented generation, long-context management, conversation memory, tool context, agent state, multimodal context, source grounding, permission-aware retrieval, context compression, and context auditability.\r\nEnsure AI systems use the right context, from the right source, with the right permissions, at the right cost, and with measurable quality.\r\nCost Optimization Frameworks Design and build cost optimization frameworks for large-scale LLM and GenAI workloads.\r\nCreate architecture patterns that reduce unnecessary token usage, redundant retrieval, repeated model calls, inefficient inference paths, and avoidable infrastructure spend.\r\nDrive model routing, token budgeting, prompt compression, context pruning, semantic caching, response caching, batch inference, async execution, fallback strategies, and cost telemetry across AI workflows.\r\nEnsure cost optimization does not compromise quality, safety, grounding, reliability, or user experience.\r\nTraining & Research Infrastructure Collaborate with research and training infrastructure teams to support large-scale model training and post-training workflows.\r\nContribute to architecture around distributed training, checkpointing, orchestration, fault tolerance, observability, data movement, evaluation infrastructure, and experiment velocity.\r\nSupport frontier model workflows across pre-training, post-training, reinforcement learning, agent training, evaluation harnesses, and large-scale experiment execution.\r\nRelease Safety, Validation & Evaluation Gates Architect validation and release systems that ensure model updates, inference engine changes, runtime images, prompt changes, context changes, and platform releases are correct, safe, performant, and regression-free.\r\nDefine release gates across correctness, numerical stability, latency, throughput, token usage, cost regression, context quality, retrieval quality, safety behavior, reliability, and model output quality.\r\nEnsure platform optimizations do not reduce safety, grounding, quality, or user trust.\r\nReliability, Observability & Production Operations Design systems that make AI infrastructure observable, debuggable, reliable, and operationally safe.\r\nDefine telemetry, tracing, dashboards, alerts, logs, profiling views, runbooks, SLOs, and post-incident learning loops.\r\nProvide visibility into prompts, context payloads, retrieved sources, token consumption, model selection, cache behavior, inference latency, GPU utilization, evaluation scores, safety events, cost, and failures.\r\nTurn production issues into stronger platform abstractions, safer rollout mechanisms, better automation, and more reliable infrastructure.\r\nAgentic & Multimodal Platform Internals Support architecture for AI agents, tool use, memory, function calling, multimodal interaction, long-running workflows, and internal or external agent deployment.\r\nWork across agent harnesses, evaluation pipelines, workflow orchestration, safety controls, state management, tool execution, memory systems, and product-facing runtime constraints.\r\nEnsure agentic and multimodal systems are reliable, observable, secure, cost-aware, and safe under real workloads.\r\nTechnical Leadership Work closely with Research, Inference, Runtime, Infrastructure, Product, Safety, Security, Technical Success, and Deployment teams.\r\nAct as a senior technical authority who can cut across layers, resolve ambiguity, identify systemic risks, and drive architecture decisions.\r\nMentor engineers and technical leads on distributed systems, performance engineering, context engineering, cost optimization, production readiness, AI platform design, and architecture trade-offs.\r\nRepresent architecture decisions through design docs, RFCs, diagrams, technical reviews, operational plans, and leadership-level summaries.\r\nRequirements Required Qualifications 10-12 years of experience in software engineering, systems architecture, ML infrastructure, distributed systems, platform engineering, inference systems, cloud infrastructure, or large-scale backend engineering\r\nStrong hands-on engineering experience with Python and at least one systems/backend language such as C++, Go, Rust, Java, or TypeScript\r\nDeep understanding of distributed systems, production infrastructure, reliability engineering, scalability, observability, and fault-tolerant architecture\r\nExperience designing or operating large-scale systems involving APIs, microservices, distributed compute, orchestration, job scheduling, caching, high-availability infrastructure, and production monitoring\r\nStrong understanding of AI/ML systems, especially model serving, inference workflows, context engineering, retrieval systems, evaluation pipelines, and production model deployment\r\nPractical understanding of GPU systems, accelerator-based workloads, CUDA/Triton-style programming, distributed inference, GPU profiling, memory optimization, and communication libraries such as NCCL or RCCL\r\nExperience with ML frameworks and serving stacks such as PyTorch, JAX, TensorFlow, Triton, vLLM-style serving, Apache Ray, Kubernetes-based serving, or internal model-serving systems\r\nAbility to debug complex problems across model behavior, runtime systems, distributed infrastructure, networking, GPU execution, context quality, retrieval quality, evaluation harnesses, and production services\r\nStrong communication skills with the ability to write clear architecture documents, evaluate trade-offs, review implementation quality, and align teams around technically sound decisions\r\nPreferred Qualifications Experience working on LLM inference, multimodal inference, agent infrastructure, AI assistants, coding agents, or frontier-model serving platforms\r\nExperience with tensor parallelism, pipeline parallelism, model sharding, KV-cache optimization, batching, speculative decoding, streaming inference, and long-context serving\r\nExperience designing context engineering platforms, prompt/version management systems, model-routing frameworks, semantic caching layers, token-budgeting systems, or LLM cost dashboards\r\nExperience profiling GPU workloads using Nsight Systems, Nsight Compute, rocprof, perf, Prometheus, Grafana, OpenTelemetry, or custom profiling systems\r\nExperience with large-scale distributed training, RL infrastructure, checkpointing, ML compiler optimizations, model graph transformations, or training runtime systems\r\nExperience designing release gates, regression detection systems, canary systems, CI/CD validation frameworks, and production safety controls for performance-sensitive infrastructure\r\nExperience with evals, model quality measurement, hallucination detection, grounding evaluation, safety testing, and model behavior monitoring\r\nTechnical Skill Areas: AI Systems: LLM serving, inference runtime, training infrastructure, post-training workflows, agent systems, multimodal models\r\nInference: batching, routing, KV-cache, streaming, latency optimization, model serving, tensor parallelism, pipeline parallelism\r\nPerformance Engineering: CUDA, Triton, GPU profiling, kernel optimization, memory bandwidth, communication libraries, distributed execution\r\nContext Engineering: prompt architecture, dynamic context assembly, RAG, memory, context compression, context ranking, source grounding, permission-aware retrieval\r\nCost Optimization: token budgeting, caching, model routing, fallback strategies, cost telemetry, batching, async workflows, cost-quality trade-offs\r\nDistributed Systems: scheduling, orchestration, reliability, fault tolerance, observability, scalability, service design\r\nML Frameworks: PyTorch, JAX, TensorFlow, Triton, vLLM-style serving, Ray\r\nInfrastructure: Kubernetes, Docker, Terraform, CI/CD, cloud platforms, Linux systems, networking, storage\r\nSafety & Validation: evals, release gates, canaries, regression testing, model behavior validation, rollout safety\r\nCandidate Profile: The ideal candidate is a senior hands-on architect who can operate across the full AI systems stack.\r\nThey should be able to discuss GPU memory bottlenecks, distributed inference, model-serving reliability, context quality, cost optimization, release validation, eval pipelines, observability, and production rollout with engineering teams, while also explaining architecture decisions clearly to senior leadership.\r\nThe candidate should not be limited to architecture diagrams. They must be capable of reviewing implementation quality, identifying bottlenecks, debugging production issues, challenging weak assumptions, and converting repeated failures into stronger platform abstractions.\r\nThis role requires the judgment of a senior architect, the debugging mindset of a systems engineer, and the ownership mindset required for production AI infrastructure.\r\nJ-18808-Ljbffr","datePosted":"2026-08-12T00:51:01.133Z","dateModified":"2026-08-12T00:51:01.133Z","hiringOrganization":{"@type":"Organization","name":"Accellor","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Mountain View","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"02efca7e0cd6041f4d832c72"},"url":"https://jobsearcher.com/jobs/02efca7e0cd6041f4d832c72"}}