Get AI‑powered advice on this job and more exclusive features.
Turing is seeking experienced software engineers to help design and validate real‑world coding tasks that push the limits of today’s large language models. You’ll work hands‑on with public GitHub repositories—standing up environments, extending test coverage, triaging issues, and building reproducible evaluation tasks that challenge model reasoning and execution.
This is a fully remote, flexible opportunity — work from anywhere, on your own schedule — while earning up to $100/hr.
What You’ll Do
- Identify and triage issues in high‑quality open‑source repositories.
- Stand up development environments (including Docker) and run/modify projects locally.
- Assess and extend unit‑test coverage to ensure reliable, verifiable benchmarks.
- Design software engineering tasks from real repository histories for AI training and evaluation.
- Optionally lead junior engineers on validation and repo triage efforts.
What We’re Looking For
- Hands‑on experience with Git, Docker, CI pipelines, and navigating complex codebases.
- Comfort contributing to and evaluating open‑source repositories.
- Strong debugging, problem‑solving, and software design instincts.
- Bonus: prior experience with LLM evaluation, developer tools, or agents.
- Excellent English communication skills for precise technical feedback.
Why You’ll Love This Role
- Remote & Flexible → Work from anywhere, at your own pace.
- Competitive Pay → Earn up to $100/hr.
- Challenging Work → Tackle complex OSS repos that stretch AI capabilities.
- Growth Potential → Lead efforts and collaborate closely with top AI researchers.
- Impact → Help define how next‑gen AI models are benchmarked and trained.
After applying, you will receive an email with a login link. Please use that link to access the portal and complete your profile.