Forward Deployment Engineer

🤖 2x Lead AI Engineers | Outside IR35 | London (1–3 days/week) | 6-Month Contract

🔐 Active SC or DV Clearance Required

We’re hiring two hands‑on Lead AI Engineers to extend and enhance an AI Operating System powered by LLMs, delivering industry‑specific solutions across defence, legal, health, infrastructure and consulting.

This is a client‑facing leadership role focused on rapidly prototyping and deploying production‑grade AI applications. You’ll translate business needs into scalable, secure AI solutions using modern frameworks and agent architectures.

• Build and extend platform functionality in Python (APIs, integrations).
• Design and deploy LLM‑powered apps using open‑source models (Llama, Qwen, Gemma) and hosted models (OpenAI, Gemini).
• Develop AI agents with tool/function calling, prompt engineering and guardrails (OpenAI Agent
  
  SDK, Lang Graph, Llama Index).
• Implement evaluation frameworks for prompt testing, output quality and agent behaviour.
• Apply RAG, Graph
  
  RAG, knowledge graphs, vector databases and data pipelines where appropriate.

• 5+ years software engineering experience.
• Proven delivery of production LLM applications.
• Strong API‑level LLM usage (tool calling, prompting, evaluation).
• Experience with agent frameworks and FastAPI (or similar).
• Client‑facing delivery and Agile team experience.

• Open‑source LLM deployment (local strategies).
• MCP, A2A protocols.
• LLM eval tooling (OpenAI Evals, Lang Smith).
• Advanced multi‑agent patterns.
• Graph databases (Neo4j, Arango
  
  DB, Neptune).