{"schemaVersion":"jobsearcher.job.v1","id":"3423bdced2ddd4a6a19e13bc","url":"https://jobsearcher.com/jobs/3423bdced2ddd4a6a19e13bc","canonicalUrl":"https://jobsearcher.com/jobs/3423bdced2ddd4a6a19e13bc","title":"Agent Engineer","description":"Job Title: Agent Engineer (AI Creative Platform)Visa Status: US Citizens, Green Card Holders (Only)Location: San Francisco, CA (100% On-site – Local Candidates Only) Job Type: Full-Time Compensation: DOEExperience: 3+ years in Production AI / Backend SystemsAbout the RoleWe are hiring an Agent Engineer for a confidential, cutting-edge AI creative platform. You will build the core agent and workflow layer behind a cloud-based creative canvas where users connect image, video, audio, text, 3D, and tool nodes into reusable production workflows.This is not a role for simple prompt wrappers. We need someone who has shipped real, production-grade AI or backend infrastructure and understands complex agent runtime behavior and model orchestration.What You Will OwnAgent Runtime Development: Build the agent runtime for a node-based creative canvas, managing planning, tool use, memory, retrieval, context, and workflow execution.Multi-Model Orchestration: Seamlessly orchestrate multiple AI models and providers across image, video, audio, text, and tool workflows.System Reliability: Design advanced routing, retries, fallbacks, latency control, cost awareness, and failure handling for generation systems.Workflow Memory: Create stateful memory that preserves project context, prior outputs, style choices, assets, and reusable templates.Quality & Evals: Build robust eval loops, regression tests, human-in-the-loop reviews, benchmarks, and creator-facing metrics.Production Optimization: Improve system resilience through queues, execution cancellation, progress states, monitoring, and graceful recovery.What We Are Looking ForProduction Experience: 3+ years of experience shipping agentic workflows, LLM applications, backend infrastructure, or AI product systems under real-world load.Tech Stack: Strong Python and/or TypeScript backend experience with deep knowledge of databases, queues, observability, and production reliability.Agent Design: Hands-on experience with runtime design components like tool calling, structured planning, context management, or DAG/workflow execution.Creative Product Judgment: Strong intuition for creative workflows where the AI needs to perform useful, complex operations on a canvas—not just chat in a text box.Strong Fit SignalsExperience with creative AI generation pipelines (Image, video, audio, TTS/STT, upscaling, lip-sync).Familiarity with node graphs, workflow engines, visual programming, or Comfy UI-style systems.Proven experience building regression tests and quality benchmarks for unpredictable AI outputs.","company":"AHU Technologies","rawCompany":"ahu technologies","city":"Millbrae","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-06-19T09:24:15.789Z","occupations":[{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"},{"code":"15-1299.08","title":"Computer Systems Engineers/Architects","slug":"computer-systems-engineers-architects"},{"code":"15-1221.00","title":"Computer and Information Research Scientists","slug":"computer-and-information-research-scientists"}],"industries":[{"code":"513210","title":"Software Publishers","slug":"software-publishers"},{"code":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"},{"code":"541810","title":"Advertising Agencies","slug":"advertising-agencies"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Agent Engineer","description":"Job Title: Agent Engineer (AI Creative Platform)Visa Status: US Citizens, Green Card Holders (Only)Location: San Francisco, CA (100% On-site – Local Candidates Only) Job Type: Full-Time Compensation: DOEExperience: 3+ years in Production AI / Backend SystemsAbout the RoleWe are hiring an Agent Engineer for a confidential, cutting-edge AI creative platform. You will build the core agent and workflow layer behind a cloud-based creative canvas where users connect image, video, audio, text, 3D, and tool nodes into reusable production workflows.This is not a role for simple prompt wrappers. We need someone who has shipped real, production-grade AI or backend infrastructure and understands complex agent runtime behavior and model orchestration.What You Will OwnAgent Runtime Development: Build the agent runtime for a node-based creative canvas, managing planning, tool use, memory, retrieval, context, and workflow execution.Multi-Model Orchestration: Seamlessly orchestrate multiple AI models and providers across image, video, audio, text, and tool workflows.System Reliability: Design advanced routing, retries, fallbacks, latency control, cost awareness, and failure handling for generation systems.Workflow Memory: Create stateful memory that preserves project context, prior outputs, style choices, assets, and reusable templates.Quality & Evals: Build robust eval loops, regression tests, human-in-the-loop reviews, benchmarks, and creator-facing metrics.Production Optimization: Improve system resilience through queues, execution cancellation, progress states, monitoring, and graceful recovery.What We Are Looking ForProduction Experience: 3+ years of experience shipping agentic workflows, LLM applications, backend infrastructure, or AI product systems under real-world load.Tech Stack: Strong Python and/or TypeScript backend experience with deep knowledge of databases, queues, observability, and production reliability.Agent Design: Hands-on experience with runtime design components like tool calling, structured planning, context management, or DAG/workflow execution.Creative Product Judgment: Strong intuition for creative workflows where the AI needs to perform useful, complex operations on a canvas—not just chat in a text box.Strong Fit SignalsExperience with creative AI generation pipelines (Image, video, audio, TTS/STT, upscaling, lip-sync).Familiarity with node graphs, workflow engines, visual programming, or Comfy UI-style systems.Proven experience building regression tests and quality benchmarks for unpredictable AI outputs.","datePosted":"2026-06-19T09:24:15.789Z","dateModified":"2026-06-19T09:24:15.789Z","hiringOrganization":{"@type":"Organization","name":"AHU Technologies","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"3423bdced2ddd4a6a19e13bc"},"url":"https://jobsearcher.com/jobs/3423bdced2ddd4a6a19e13bc"}}