Development - App Dev - Java - Lead
Job Title: Principal / Senior AI Engineer (Agentic AI | Python | AWS)Location: Richmond, VA or McLean, VA (Hybrid – Local Candidates Only)Duration: 7 Months ContractRole Overview:We are seeking a highly experienced Principal / Senior AI Engineer to join a fast-paced, cross-functional engineering team within a leading enterprise organization. This is a hands-on builder role focused on designing and delivering Agentic AI solutions and transforming Generative AI prototypes into scalable, production-grade systems.The ideal candidate will have deep expertise in Python full-stack development, LLMs, and AWS cloud architecture, along with proven experience building reliable, secure, and high-performance AI-driven applications.Key ResponsibilitiesAgentic AI & Application Development:Design, develop, and deploy AI-driven applications and multi-agent systems using frameworks like LangChain, LangGraph, and CrewAIBuild agentic workflows to automate complex engineering and business processesRAG & LLM Engineering:Develop and optimize Retrieval-Augmented Generation (RAG) pipelines using Amazon Bedrock and vector databases (OpenSearch, Pinecone)Work with LLMs (GPT, Claude, Llama) for real-world enterprise use casesImplement LLM orchestration, tool usage, and function callingFull-Stack & Backend Development:Develop scalable applications using Python (frontend & backend), FastAPI, Pydantic, and async programmingEnable real-time AI capabilities including streaming responses and APIsAI Integration & Enterprise Systems:Integrate AI solutions with enterprise platforms such as ServiceNow, CMDB, and JIRACollaborate with frontend teams (React) to deliver intuitive AI-powered user experiencesResponsible AI & Governance:Implement guardrails including prompt engineering, content moderation, bias detection, and output validationEnsure compliance with enterprise security and AI governance standardsObservability, Evaluation & MLOps:Build evaluation frameworks using Ragas, DeepEvalImplement observability using LangSmith, OpenTelemetryDevelop and maintain CI/CD pipelines for AI/ML workflows, prompt versioning, and deploymentEngineering Excellence:Contribute to system design, architecture, and best practicesProvide technical leadership and AI expertise across teamsDrive improvements in engineering and operational excellenceRequired QualificationsMust have previous client experience working for this customer in the past 5 years10+ years of overall software engineering experience7+ years of strong hands-on experience with Python (full-stack/backend)2+ years of hands-on experience in AI / Generative AI / LLMs5+ years of experience with AWS cloud (Bedrock, SageMaker, Lambda, etc.)Proven experience building scalable, production-grade applicationsStrong knowledge of system design, distributed systems, and backend architectureTechnical Skills:AI / GenAI: GPT-series, Claude, Llama, Hugging Face Transformers, PEFTAgent Frameworks: LangChain, LangGraph, CrewAI, multi-agent systems, tool usage, function callingBackend / Full Stack: Python 3.10+, FastAPI, Pydantic, Async programmingCloud & Infrastructure: AWS (Bedrock, SageMaker, Lambda, RDS, pgvector), Serverless architectureVector Databases: OpenSearch, PineconeObservability & Evaluation: LangSmith, OpenTelemetry, Ragas, DeepEvalPreferred QualificationsExperience building production-grade AI/ML platformsHands-on experience with LLM fine-tuningExperience with multi-agent AI systemsFamiliarity with CI/CD pipelines and MLOps practicesPrior experience with Capital One (highly preferred)Experience with enterprise-scale integrations and platforms