Key skills
PythonAIMLGenAILLMOpenAIAnthropicRAGAgenticAutoGenLangGraphChromaPineconeWeaviatePhoenixAzureKubernetesDockerGitVersion ControlCI/CD
About this role
Location
McLean, VA (On-site / Hybrid)
Role Type
Individual Contributor Developer
Employment
Contract / Full-Time
Primary Skills
Python RAG MCP AI Agents
About the Role
Client is seeking a skilled GenAI Engineer to join its technology team in McLean, VA. In this individual contributor role, you will focus on the day-to-day development and implementation of AI-powered solutions. Architecture and system design decisions are handled by the client's senior architecture team - your mandate is to build, integrate, test, and iterate on AI features at pace. If you are a strong Python developer with hands-on experience in RAG pipelines and modern AI tooling, this is your opportunity to work on impactful solutions at one of the nation's leading mortgage enterprises.
Key Responsibilities
- Develop, test, and maintain AI/ML features and integrations as directed by the architecture team.
- Build and optimize Retrieval-Augmented Generation (RAG) pipelines for enterprise knowledge retrieval use cases.
- Implement and integrate Model Context Protocol (MCP) servers and clients to extend AI model capabilities.
- Write clean, well-documented Python code following established coding standards and best practices.
- Integrate AI components with existing internal systems, APIs, and data sources.
- Collaborate with architects, product owners, and business stakeholders to translate requirements into working solutions.
- Participate in code reviews, testing, and QA cycles to ensure reliability and performance.
- Monitor, debug, and iterate on deployed AI features based on performance metrics and user feedback.
- Maintain technical documentation for developed components and integrations.
- Stay current with the rapidly evolving AI/LLM tooling landscape and propose improvements where applicable.
Required Qualifications
- Strong proficiency in Python for backend and AI/ML development.
- Experience working with REST APIs, message queues, and cloud-based infrastructure.
- Familiarity with version control (Git) and CI/CD workflows.
- Hands-on experience building and deploying RAG (Retrieval-Augmented Generation) pipelines, including chunking strategies, embedding models, and vector stores.
- Working knowledge of Model Context Protocol (MCP) - building or consuming MCP servers/clients to connect LLMs to external tools and data.
- Experience with at least one major LLM provider API (OpenAI, Anthropic, Azure OpenAI, etc.) for inference and prompt engineering.
- Familiarity with vector databases such as Chroma, Pinecone, Weaviate, pgvector, or equivalent.
- Experience building scalable, production-grade AI agents using frameworks such as LangGraph, CrewAI, AutoGen, or custom orchestration layers.
- Familiarity with agentic design patterns: tool use, memory management, multi-step reasoning, and human-in-the-loop workflows.
- Background in financial services, mortgage, or regulated industry environments.
- Experience with LLM observability and evaluation tools (e.g., LangSmith, Phoenix, RAGAS).
- Knowledge of containerization and deployment (Docker, Kubernetes).