AI Engineer (Hybrid, 12‑month contract)

About the role

We are looking for an AI Engineer with a strong software engineering background to join a fast‑moving team in London. The position is hybrid (three days in‑office) on a 12‑month contract (inside IR35) and blends platform engineering with business‑facing AI delivery.

Key responsibilities

• Design, build and maintain core AI platform components such as the LLM gateway, MCP connector layer, observability tooling, and privacy proxy.
• Develop and harden MCP connectors for data sources (M365, Salesforce, Moody’s, internal systems) through PoC, pilot and GA stages.
• Create AI‑powered tools and workflows for business teams, turning use cases into governed, production‑ready applications.
• Integrate with Databricks/Unity Catalog as the data foundation for AI features.
• Write clear specifications, ensure test coverage and support prompt engineering, evaluation and iterative improvement of deployed AI features.
• Collaborate with the engineering squad to shift outsourced delivery to in‑house capability.

Required profile

• Hands‑on experience building production‑grade AI solutions using LLM APIs (Anthropic, OpenAI or similar).
• Proven ability to write clean, production‑quality Python code.
• Familiarity with data platforms such as Databricks and safe data exposure to LLMs.
• Understanding of security and governance concerns (prompt injection, data boundaries, RBAC).
• Experience in financial services or other regulated environments is a plus.

Required skills

• Python development
• LLM APIs (Anthropic, OpenAI)
• Databricks / Unity Catalog
• M365, Salesforce, Moody’s integration
• MCP connector patterns
• Observability and evaluation tooling for AI systems
• Prompt engineering and agentic frameworks
• Security and governance (RBAC, prompt‑injection mitigation)