Remote C++ Bench Engineer for AI Code Evaluation

Turing; United States; Remote; USD 46,000 - 68,000; Part time

Benefits offered by this job

Fully remote

Job summary

Turing is seeking experienced software engineers for a contractor assignment to analyze GitHub issues and assess LLM performance on real code. The role emphasizes hands-on engineering, environment automation, issue triaging, and evaluating test coverage in open-source projects.

Expect 2–3 week duration with a 40-hour/overlap requirement, fully remote work, and a pay model of $25 per approved task. Start date is next week, with potential collaboration with AI researchers on repository challenges.

Qualifications

• 2+ years of overall software experience.
• Strong in at least one language: C++.
• Proficient with Git, Docker and basic pipeline setup.
• Able to understand and navigate complex codebases.
• Comfortable running and testing real-world projects locally.
• Experience with open-source projects is a plus.

Responsibilities

• Analyze and triage GitHub issues across trending libraries.
• Set up repos, Dockerize and configure environments.
• Evaluate unit test coverage and quality.
• Modify and run code locally to assess LLM performance.
• Collaborate with researchers to pick challenging repositories.

Skills

C++

Git

Docker

Codebase navigation

Local testing

Tools

Git

Docker

CI/CD pipelines

Job description

Turing is seeking experienced software engineers for a contractor assignment to analyze GitHub issues and assess LLM performance on real code. The role emphasizes hands-on engineering, environment automation, issue triaging, and evaluating test coverage in open-source projects.

Expect 2–3 week duration with a 40-hour/overlap requirement, fully remote work, and a pay model of $25 per approved task. Start date is next week, with potential collaboration with AI researchers on repository challenges.