AI Engineer

This is a fully remote position, open to applicants in Washington.

📋 Description

• Create and develop agentic systems—multi-step agents that plan, utilize tools, gather context, and execute actions with suitable human-in-the-loop checkpoints.

• Construct MCP servers and clients to securely present client data, internal tools, and APIs to LLMs in a standardized and auditable manner.

• Deliver LLM-driven applications: copilots, document intelligence, search functionalities, summarization, and workflow automation.

• Design and manage RAG pipelines—chunking, embeddings, vector storage, retrieval, reranking, and grounding.

• Integrate model APIs (OpenAI, Anthropic, Bedrock, Azure OpenAI, open-weight models) and select the appropriate model based on quality, latency, and cost considerations.

• Develop evaluations and observability for agents and AI features to monitor production performance and identify regressions.

• Utilize prompt engineering, structured outputs, function/tool invocation, and guardrails to ensure predictable agent behavior.

• Write production-grade Python backends and APIs that offer AI capabilities to web and mobile clients.

• Collaborate with engineers, designers, and product teams to define the scope of what AI should (and should not) accomplish in a specific product.

• Contribute to the establishment of responsible AI practices for federal applications—emphasizing privacy, security, auditability, and human oversight.

⛳️ Requirements

• Over 5 years of professional software engineering experience, including at least 1 year of deploying LLM-based or AI-powered features into production.

• Practical experience in designing or building agentic systems—tool invocation, multi-step reasoning, planning loops, or agent orchestration (LangGraph, CrewAI, OpenAI Agents SDK, Claude tool use, or similar).

• Familiarity with the Model Context Protocol (MCP)—or the ability to learn it quickly, coupled with a broader understanding of agent/tool standards.

• Proficient in Python with experience in building and deploying backend services and APIs (FastAPI, Flask, or equivalent).

• Hands-on experience with at least one major LLM provider (OpenAI, Anthropic, Bedrock, Azure OpenAI, Vertex, or open-weight models via vLLM/Ollama).

• Knowledge of RAG: embeddings, vector databases (pgvector, Pinecone, Weaviate, Qdrant, or similar), and retrieval evaluation.

• Comfortable with prompt engineering, structured outputs (JSON mode, schemas), and tool/function invocation.

• Experience in writing evaluations—even lightweight ones—for non-deterministic systems.

• Strong SQL skills with experience in handling relational and unstructured data.

• Familiarity with at least one cloud platform (AWS, Azure, or GCP).

• Proficient in Git, code review, and modern collaborative workflows.

• Excellent written and verbal communication skills—capable of explaining AI trade-offs to non-technical stakeholders.

🏝️ Benefits

• Competitive salary.

• Contribution towards health benefits.

• Option to work from anywhere in the US.

• High-visibility federal projects that create a real impact.

• Join a small team where your ideas can be implemented.

• Ample exposure to the latest AI tools and models.