AI Engineer

AI Engineer Location: Remote (US only) Compensation: $130,000 to $150,000

A small, technical digital services firm working with federal and commercial clients is hiring an AI Engineer to build and ship production-grade applications powered by large language models.

This is a hands-on engineering role. You will design agentic systems, build MCP servers and clients, maintain RAG pipelines, and write the Python backends that expose AI capabilities to real users, including senior government stakeholders. You will also help shape how the organization adopts generative AI responsibly across an active client portfolio.

This is not a research role. No foundation model training. You will be designing and shipping systems that people depend on, and you will have a direct voice in how that gets done.

What you will build:

• Multi-step agents that plan, call tools, retrieve context, and take action with human-in-the-loop checkpoints
• MCP servers and clients that securely connect models to client data, internal tools, and APIs
• RAG pipelines covering chunking, embeddings, vector stores, retrieval, reranking, and grounding
• LLM-powered features including copilots, document intelligence, search, summarization, and workflow automation
• Evals and observability so the team knows what is working in production and what is regressing

What you need:

• 5 or more 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 using tool calling, multi-step reasoning, planning loops, or agent orchestration (LangGraph, CrewAI, OpenAI Agents SDK, Claude tool use, or equivalent)
• Working knowledge of MCP or demonstrated ability to pick it up quickly
• Strong Python and experience building and deploying backend services and APIs (FastAPI, Flask, or similar)
• Experience with at least one major LLM provider: OpenAI, Anthropic, Bedrock, Azure OpenAI, Vertex, or open-weight models
• Working knowledge of RAG: embeddings, vector databases (pgvector, Pinecone, Weaviate, Qdrant, or similar), and retrieval evaluation
• Comfort with prompt engineering, structured outputs, and tool/function calling
• Experience writing evals for non-deterministic systems
• Solid SQL and comfort with relational and unstructured data
• Familiarity with at least one cloud platform: AWS, Azure, or GCP
• Strong written communication -- you can explain AI tradeoffs to non-technical stakeholders

Nice to have:

• Experience authoring MCP servers for non-trivial systems
• Eval and observability platform experience (Braintrust, LangSmith, Langfuse, Arize, or custom)
• Multi-agent orchestration and experience reasoning about agent failure modes
• Fine-tuning, distillation, or LoRA experience
• Docker, Kubernetes, and CI/CD for AI workloads
• TypeScript/Node for full-stack AI features
• Background supporting federal or government clients
• Awareness of NIST AI RMF, FedRAMP, or related responsible AI frameworks

Requirements:

• Must be a US citizen or legal resident, able to work domestically
• Must be able to attain a low-level security clearance