Agentic AI Engineer (Horizon AI)

Level: Staff (MTS 4) · Reports to: Chief AI Officer, later the Senior Engineering Manager

The role. Build agents and the tools they use. Hands-on work on the reasoning layer, alongside the Agent Fleet Lead, with regular embeds beside the operators whose decisions you are encoding.

You will

• Extend and maintain the tool surface across our infrastructure and business systems, which needs ongoing development and consolidation

• Implement agents that diagnose fleet conditions and produce recommended actions with visible reasoning

• Translate operator runbooks and tacit knowledge into agent behaviour, largely by sitting with the operators

• Build evaluation fixtures from real historical incidents and measure agent performance against them

• Rotate through Systems and SRE embeds

You have

• Shipped production software with LLMs in the loop, including the unglamorous parts: retries, timeouts, malformed output, token and cost control

• Strong Python

• Experience building tool or function-calling interfaces that give models structured access to external systems

• A demonstrable recent record of building and shipping rather than designing and reviewing

• Curiosity about infrastructure and willingness to learn it from the people who run it

Nice to have: async Python at scale, retrieval pipelines, OpenTelemetry, prior work on evaluation harnesses