Description
Intergral UK is hiring a full-time, remote AI Evaluation & Benchmarking Engineer in the United Kingdom to build automated evaluations and benchmarking systems for its AI-led observability platform, OpsPilot. The role covers agentic AI evaluation, synthetic workloads, ground truth, model and workflow benchmarking, OpenTelemetry-based environments, product telemetry, and continuous measurement of quality, reliability, latency, cost, and customer outcomes. The engineer will work independently with AI, software, platform, and SRE teams, build evaluation tooling, and help identify regressions and improvement opportunities. The position requires around three or more years of relevant technical experience, with no visa sponsorship.
