The role
Turing needs experienced engineers to evaluate AI coding agents, review their code and write the rubrics and preference data that improve the models. It's a roughly three-month contract with at least 6 hours of Pacific Time overlap.
What you'll do
- Evaluate AI-generated code and agent behavior across real-world repositories
- Identify technical errors, weak approaches and recurring model failure modes
- Compare model outputs and explain why one solution is better
- Create rubrics and preference data used to improve coding models
- Build pipelines supporting data generation and evaluation workflows
What they're looking for
Must-haves
- Hands-on software engineering in substantial real-world codebases
- Strong in Python, TypeScript/JavaScript, Go or another major language
- Strong code-review skills and technical judgment
- Clear written communication
- Experience using modern LLMs or AI coding tools
Nice to have
- Experience with LLM evaluation or coding agents
- Background in RLHF, preference data or post-training
- Experience with rubric design
Skills and platforms
- Python
- TypeScript
- JavaScript
- Go
- Software Engineering
- Code Review
- LLM
- AI Coding Tools
- RLHF
- Preference Data
- Rubric Design
- Data Generation
- Technical Judgment
- Communication
- Coding Agents
The company

Turing
Technology, Information and Internet
Turing is one of the world’s fastest-growing AI companies accelerating the advancement and deployment of powerful AI systems.
Summarised by Jobs That Travel from Turing's listing.






