Full Stack Software Engineer, Evaluation Tools

Highlights

• Build internal products powering evaluation of every major AI Driver release.
• Own search and agentic tooling that turns driving issues into test suites.
• Scale scenario mining to millions of scenarios for model developers.

What they offer

• Meaningful equity sharing in long-term success
• Salaries benchmarked against the market annually
• Relocation support where applicable
• Hybrid working with core hours
• Learning and development budgets for training and conferences
• Comprehensive health, dental, parental leave and wellbeing benefits

Ideal candidate

Product-minded full-stack builder who thrives in ambiguity and owns features end-to-end. Passionate about autonomy and empowering AI researchers with intuitive evaluation tools.

Requirements

• Strong development skills in Python, TypeScript, JavaScript and React or similar frameworks
• Strong SQL skills with database design and optimisation
• Experience designing and building production-level full-stack systems and high-performance APIs
• Track record of building robust, maintainable systems with engineering best practices
• Excellent communication and collaboration skills across time zones
• Comfortable working independently in fast-paced, ambiguous environments
• Power user of AI development tools with mindset for AI-augmented workflows