Remote JavaScript Engineer

We are seeking experienced software engineers, ideally at a tech lead level, to contribute to projects focused on building LLM evaluation and training datasets. These datasets are designed to train LLMs for realistic software engineering tasks, including developing verifiable software engineering tasks from public repository histories using a synthetic approach with human-in-the-loop, and expanding dataset coverage across various programming languages and difficulty levels.

In this role, you will engage in hands-on software engineering, automating development environments, triaging issues, and evaluating test coverage and quality. You will analyze and triage GitHub issues from popular open-source libraries, set up and configure code repositories with Dockerization, and evaluate unit test coverage and quality. A key part of the role involves modifying and running codebases locally to assess LLM performance in bug-fixing scenarios and collaborating with researchers to identify challenging repositories and issues for LLMs. Opportunities to lead junior engineers are also available.

Why join Turing? Be at the forefront of evaluating LLM interaction with code, shaping the future of AI-assisted software development. This position offers a unique blend of practical software engineering and AI research.

Required Skills: Minimum 3 years of overall experience, strong JavaScript/TypeScript proficiency, Git, Docker, basic software pipeline setup, ability to navigate complex codebases, and experience running/modifying/testing projects locally. Prior contributions to or evaluation of open-source projects are a plus.

Nice to Have: Experience with LLM research/evaluation or building/testing developer tools and automation agents.

Perks include a fully remote work environment and the opportunity to work on cutting-edge AI projects with leading LLM companies.

Commitment: Minimum 4 hours per day, 20 hours per week, with a 4-hour overlap with PST. Options for 20, 30, or 40 hours per week.