About The Position

Turing is seeking experienced, hands-on software engineers to evaluate and improve AI coding models. Instead of primarily building production applications, the engineer will work with coding agents across real-world repositories, review generated code and agent behavior, assess technical correctness, identify failure modes, and create evaluation signals and feedback to improve model performance. The role requires explaining whether an agent understood a task, chose an appropriate approach, and produced code that is correct, robust, and maintainable. The engineer will also help create evaluation criteria and preference data, build and maintain infrastructure for data-generation and evaluation workflows, and communicate findings to researchers and engineers. The engagement is an independent contractor role for approximately three months, with 40 hours per week preferred and at least six hours of Pacific Time overlap. The position is open to candidates in North America, LATAM, or India, and is expected to start as soon as possible.

Requirements

  • At least 5 years of hands-on software engineering experience.
  • Strong proficiency in Python, TypeScript/JavaScript, Go, or another major production language.
  • Experience working in substantial real-world codebases.
  • Strong code-review skills and technical judgment.
  • Ability to clearly explain why an implementation is correct, incorrect, or could be improved.
  • Strong written communication.
  • Availability of 40 hours per week is preferred, with at least 6 hours of Pacific Time overlap.
  • Provide a specific hourly rate expectation.

Nice To Haves

  • Experience using modern LLMs or AI coding tools.
  • Experience with LLM evaluation, coding agents, RLHF, preference data, rubric design, or post-training.

Responsibilities

  • Evaluate AI-generated code and solutions across real-world software repositories.
  • Review agent behavior, tool usage, and code changes for correctness and quality.
  • Identify technical errors, weak approaches, and recurring model failure modes.
  • Compare model outputs and explain why one solution is better than another.
  • Create and refine rubrics and evaluation criteria for coding tasks.
  • Produce high-quality evaluation and preference data used to improve coding models.
  • Build and maintain pipelines and infrastructure supporting data generation, collection, and evaluation workflows.
  • Synthesize findings from data work into clear write-ups, updates, and recommendations for the team.
  • Collaborate with researchers and engineers to translate qualitative judgment into scalable processes.
  • Share clear, actionable findings with AI researchers and engineers.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service