Senior Software Engineer, AI Evaluation Infrastructure

About the role

Turing is hiring a senior backend engineer to build the infrastructure frontier AI labs use to evaluate coding agents and language models, including benchmark datasets, large-scale agent evaluation runs and automated task quality checks. You would own features end to end, from data model and background jobs to the user-facing screens.

What you'll do

• Design and ship features across the stack: data model, API, background workers and UI when needed.
• Run agent trials in sandboxed environments, score results and aggregate thousands of runs into trustworthy outputs.
• Strengthen benchmark quality with verifiers, rubric-based grading and LLM-as-a-judge approaches.
• Integrate new models, agents and benchmarks in a generalizable way, avoiding special cases.
• Keep the system fast and reliable with efficient queries, safe migrations and solid concurrency; review teammates' pull requests.

Requirements

• Typically 5+ years building and operating production backend systems, owning a service from design through on-call.
• Strong Python, plus experience with Django or similar, PostgreSQL and a task queue such as Celery.
• Hands-on LLM evaluation experience: building benchmark tasks, scoring agent trials, comparing results (Harbor, Terminal-Bench, SWE-bench or Inspect a plus).
• Judgment to spot ambiguous instructions, gameable verifiers and leaked answers.
• Comfort touching a TypeScript/React frontend and clear written communication.