In this role, your Python expertise will directly influence how AI models understand and generate code.

Youll design and implement solutions, analyze model outputs, and shape evaluation strategies that determine how AI performs on real-world coding tasks.

What Youll Do :

- Write clean, efficient Python code to generate datasets and implement solutions from prompts.

- Run model evals, analyze results, and document clear rationales.

- Compare and rank LLM outputs; propose improved responses and prompts.

- Collaborate with AI researchers and developers to refine evaluation strategies and tooling.

What Were Looking For :

- 3+ years professional Python with strong coding, testing, and debugging skills.

- Comfort with async programming, performance optimization, and refactoring best practices.

- Familiar with Pythons ecosystem (packaging, tooling, linters, formatters).

- Excellent problem-solving and English communication.