AI Engineer

About the job

Responsibilities

• Design and build agentic systems with multi-step planning, tool usage, context retrieval, and human-in-the-loop checkpoints.
• Build MCP servers and clients to securely expose client data, internal tools, and APIs to LLMs in an auditable manner.
• Ship LLM-powered applications such as copilots, document intelligence tools, search functionalities, summarization, and workflow automation.
• Design and maintain RAG pipelines, including chunking, embeddings, vector stores, retrieval, reranking, and grounding.
• Integrate model APIs from various providers (OpenAI, Anthropic, Bedrock, Azure OpenAI, open-weight models) and select the appropriate model based on quality, latency, and cost.
• Develop evaluations and observability for AI features to monitor production performance and regressions.
• Apply prompt engineering, structured outputs, function/tool calling, and guardrails to ensure predictable agent behavior.
• Write production Python backends and APIs to expose AI capabilities to web and mobile clients.
• Collaborate with cross-functional teams (engineers, designers, product managers) to define AI product scope and capabilities.
• Contribute to shaping responsible AI practices for federal use, focusing on privacy, security, auditability, and human oversight.

Requirements

• 5+ years of professional software engineering experience, with at least 1 year shipping LLM-based or AI-powered features to production.
• Hands-on experience designing or building agentic systems (e.g., tool calling, multi-step reasoning, agent orchestration with LangGraph, CrewAI, OpenAI Agents SDK, Claude tool use).
• Working knowledge of the Model Context Protocol (MCP) or ability to quickly learn it, with familiarity in agent/tool standards.
• Strong Python skills and experience building/deploying backend services and APIs (e.g., FastAPI, Flask).
• Hands-on experience with at least one major LLM provider (OpenAI, Anthropic, Bedrock, Azure OpenAI, Vertex, or open-weight models).
• Working knowledge of RAG, including embeddings, vector databases (e.g., pgvector, Pinecone, Weaviate, Qdrant), and retrieval evaluation.
• Comfort with prompt engineering, structured outputs (JSON mode, schemas), and tool/function calling.
• Experience writing evaluations for non-deterministic systems.
• Solid SQL skills and experience with relational and unstructured data.
• Familiarity with at least one cloud platform (AWS, Azure, or GCP).
• Proficiency with Git, code review, and modern collaborative workflows.
• Strong written and verbal communication skills, capable of explaining AI tradeoffs to non-technical stakeholders.
• Must be a US Citizen or legal resident, able to work domestically.
• Must be able to attain a low-level security clearance.
• Must work from the United States.

Benefits

• Work from anywhere.
• Opportunity to work on high-visibility projects with significant impact.
• Competitive salary range ($130,000 - $200,000+).
• Comprehensive medical, dental, vision, life, and disability insurance.
• Up to 20+ days of PTO annually.
• 401(k) retirement savings plan.
• FSA/HSA and commuter benefit options.
• Professional development opportunities, certifications, and continuous learning support.
• Company-provided technology and access to productivity and AI tools.
• Additional bonus based on performance.