About the job

Tracer is hiring a Lead AI Software Engineer in London to architect and lead the development of core agentic AI systems that transform production data pipeline alerts into grounded, evidence-based root cause analyses (RCA) and actionable fix suggestions. As an early-stage, venture-backed startup, Tracer is building autonomous AI agents that investigate incidents before engineers are even paged, correlating telemetry, infrastructure signals, and workflow graphs to filter noise and identify what truly matters. In this role, you will own the end-to-end design and implementation of alert ingestion and normalization, context enrichment, hypothesis orchestration, investigation execution runtime, artifact generation, and reporting systems. The tech stack includes Python with LangGraph for multi-agent orchestration, Rust for high-performance systems, ClickHouse for high-volume event storage, AWS and Terraform for infrastructure automation, and Next.js with TypeScript for frontend collaboration. The ideal candidate has 5+ years (ideally 10+) of professional software engineering experience, strong backend and distributed systems foundations, experience shipping production-grade systems at high velocity, and a high-ownership startup mindset. The position offers a total compensation range of £150,000–£220,000+ including meaningful equity (typically 0.3%–2%+), 30 days annual leave, health insurance, visa sponsorship, team offsites, and the opportunity to play a foundational role in building a world-class AI-powered product from the ground up.