AI Engineer

AI Engineer Generative& Agentic WorkflowsLocation: Austin, TX (Hybrid)Job Type: W2 Contract roleVisa: Independent Visa onlyGenerativeAI Core DevelopmentModel Optimization & Fine-Tuning: Fine-tune, distill, and optimize open-source andproprietary foundation models (e.g., Llama, Claude, GPT-4, Mistral) usingtechniques like PEFT/LoRA and RLHF/DPO.Retrieval-Augmented Generation (RAG): Build scalable, low-latency Hybrid RAG architecturesintegrating vector databases, graph databases, and semantic routing forcomplex domain contexts.Multimodal Pipelines:Design and deploy multimodal pipelines (text, vision, audio, structureddata) to extract insights and generate rich artifacts.AgenticAI & Autonomous SystemsMulti-Agent Architectures: Design and deploy multi-agent orchestration frameworks(e.g., LangGraph, AutoGen, CrewAI, Semantic Kernel) with dedicated roles,shared memory, and cross-agent negotiation strategies.Planning & Reasoning Protocols: Implement advanced reasoning paradigms such asChain/Tree/Graph-of-Thought, ReAct loops, self-reflection, andreflection-based error correction.Tool Augmentation & Function Calling: Connect agents to external APIs, databases, softwareenvironments, and browser tools, enabling reliable function calling,schema validation, and tool execution.Human-in-the-Loop (HITL) Workflows: Build human-in-the-loop safety checkpoints, approvaltriggers, and oversight interfaces into autonomous agent loops.PlatformPerformance, Guardrails & MLOpsAgentic Observability & Evaluation: Set up rigorous evaluation frameworks (LLM-as-a-judge,trajectory tracing, latency profiling) using tools like LangSmith,Phoenix, or Arize.Guardrails & Alignment: Implement strict safety, hallucination mitigation,context-window optimization, and prompt injection defenses using guardrailframeworks (e.g., NeMo Guardrails, Guardrails AI).Production Deployment: Scale agent workflows on cloud infrastructure(AWS/GCP/Azure) with async task queues, durable execution state, andlow-latency API integration.Key Skills & TechnologiesLanguagesPython (Expert), TypeScript / Node.js (Plus)Gen AI FrameworksPyTorch, Hugging Face Transformers, vLLM, Ollama,LangChain, LlamaIndexAgentic FrameworksLangGraph, AutoGen, CrewAI, Semantic Kernel, TemporalDatabases & SearchQdrant, Pinecone, Milvus, Weaviate, Pgvector, Neo4jInfrastructure & MLOpsDocker, Kubernetes, Ray, FastAPI, LangSmith, MLflow,AWS/GCP/AzureExperience& QualificationsExperience: 6+ years of professional software engineering experience, with 2+ yearsdedicated to building and deploying Gen AI and/or LLM applications inproduction.Proven Track Record:Experience building stateful LLM applications, custom RAG systems, orautonomous agentic workflows deployed to real users.Strong Algorithmic Foundation: Solid understanding of transformer architectures,attention mechanisms, vector embeddings, and non-deterministic statemachine design.Problem-Solving Mindset: Comfort dealing with model non-determinism, edge casesin tool calling, and designing robust fallback mechanisms.