Ai/Llm Engineer — Python, Langchain, Rag, Aws Lambda (Santa …, Santa Fe Capital

Project BriefWe're building AI-powered products, primarily leveraging off-the-shelf LLM APIs, while also partnering with our Applied Science teams to integrate custom models when needed.
You'll own end-to-end development of AI features — from prototyping to production — focused on reliability, accuracy, and scalable delivery.Must-HavesStrong Python engineering skills and experience delivering production systemsHands‐on experience building with LLM APIs (OpenAI, Anthropic, etc.) and deploying AI features end‐to‐endExperience with LangChain / LangGraph — including Prompt Engineering, Token Management, and Agent creation with tool‐based workflowsExperience building agentic workflows (tool use, routing, memory, safety/guardrails), ideally with MCPSolid understanding of RAG concepts — retrieval, chunking, embeddings, re‐ranking, and evaluationPractical AWS experience, especially AWS Lambda and serverless architecture patternsBackend engineering experience: RESTful API design, webhook integration, JWT, pytest, and observability tools like SentryExperience doing Git repository analysis — understanding large codebases, debugging, refactors, and code healthComfortable working in fast‐moving product environments with high ownershipNice to HaveNextJS and TypeScript for frontend components and integrationAWS CDK for infrastructure‐as‐code and deploymentBroader AWS services knowledge: S3, CloudWatch, IAM, API GatewayExperience with NoSQL databasesExperience integrating or serving custom models (inference, model endpoints, monitoring)Familiarity with evaluation frameworks (offline tests, human feedback loops, regression suites)Strong software engineering fundamentals: testing, CI/CD, observability, performanceWhat You Will DoPlan and develop applications that include custom AI components — orchestration, evaluation, tooling, and integrationsBuild intelligent agents using LLMs and the MCP framework to enable context‐aware automation and decision‐makingAutomate internal workflows and operational processes using Python and AWS LambdaDevelop and improve RAG‐based chatbots to increase response accuracy, grounding, and consistencyCollaborate with Applied Science teams to productionize custom models and connect them with product systemsDesign and maintain multi‐agent AI pipelines, including fallback and graceful degradation strategies for reliability
#J-*****-Ljbffr