Software Engineer

Turing

1d

About The Position

Turing builds infrastructure used by frontier AI labs to evaluate coding agents and language models, including benchmark datasets, large-scale agent evaluation runs, and automated task quality checks. The Software Engineer will own features across the stack, from data models and background jobs to user-facing screens. This role is suited to an experienced engineer who can work independently, make sound tradeoffs, and turn loosely defined requests into shipped, tested, reliable work.

The engineer will design and deliver end-to-end features; improve agent and model evaluation, including sandboxed trials and scoring; and strengthen benchmark task quality checks through verifiers and rubric-based or LLM-as-a-judge grading. The role also includes integrating models, agents, and benchmarks in a generalizable way, maintaining performance and reliability as usage grows, and reviewing teammates’ pull requests against engineering guidelines.

The team applies written engineering guidelines consistently, keeps business logic in services and hot paths efficient, and expects lint and tests to pass before pull requests are ready. It favors simple designs, consistent vocabulary across code, API, and UI, and deleting code over adding it when practical. A strong first month involves merging several changes with light review and becoming confident changing one area of the system independently.

Turing describes its values as client first, startup speed, and AI forward. Advantages of joining include working on frontier AI research and enterprise applications, opportunities to showcase work at conferences such as ICLR, ICML, and NeurIPS, and collaboration with colleagues with deep AI experience. The posted compensation is “$xxx,000 - $xxx,000 Base Salary + Equity”; the amounts are unspecified.

Requirements

• At least 5 years of experience building and operating production backend systems.
• Ownership of at least one service from design through on-call.
• Bachelor’s degree or higher in Software Engineering, Computer Science, or a related field.
• Strong Python skills and experience with Django or a similar framework, PostgreSQL, and a task queue such as Celery.
• Hands-on LLM evaluation experience beyond calling a model API, including understanding benchmark task construction, agent trial scoring, and aggregation and comparison of results.
• Ability to identify ambiguous task instructions, weak or gameable verifiers, leaked answers, and checks that pass for the wrong reason.
• Ability to make pragmatic design tradeoffs, extend existing systems before adding new ones, and explain what was not built.
• Ability to take ownership of loosely defined requests, locate relevant code, ask questions when answers affect design, and complete implementation including migrations, tests, and edge cases.
• Ability to quickly adopt written team conventions for naming, structure, tests, and error handling.
• Comfort working with a TypeScript and React frontend when a change affects the UI; frontend specialization is not required.
• Clear written communication, including explanations of why a change is being made.

Nice To Haves

• Experience running agents in sandboxed or containerized environments such as Docker, Kubernetes, Modal, or Daytona.
• Experience with LLM-as-a-judge or rubric-based grading and reducing judge bias and noise.
• Familiarity with coding agents such as Claude Code, Codex, or OpenHands, and with MCP.
• Experience with distributed job scheduling, concurrency limits, or database locking at scale.
• Contributions to open-source evaluation or infrastructure projects.
• Experience with Harbor, Terminal-Bench, SWE-bench, Inspect, or a similar evaluation harness.

Responsibilities

• Design and ship features end to end, including data models, APIs, background workers, and UI changes where needed.
• Build and improve agent and model evaluations, including trials in sandboxed environments, scoring, and aggregation of results from many runs.
• Improve benchmark task quality checks using verifiers, rubric-based grading, and LLM-as-a-judge grading; assess whether tasks are clear, solvable, and fair to score.
• Integrate new models, agents, and benchmarks using approaches that generalize rather than relying on one-off special cases.
• Maintain system performance and reliability as usage grows, including efficient queries, safe migrations, and concurrency that holds up under load.
• Review teammates’ pull requests against engineering guidelines and help maintain codebase consistency.
• Complete work including migrations, tests, and user-facing edge cases.
• Write pull request descriptions and design notes that explain the rationale behind changes.

Benefits

• Equity is included in the stated compensation package.
• Opportunity to work on frontier AI research and showcase work at conferences such as ICLR, ICML, and NeurIPS.
• Opportunity to apply frontier AI innovation to enterprise challenges.
• Collaboration with colleagues with deep AI experience from Google, Meta, Amazon, and other technology companies.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior