AI Safety Benchmark Engineer

Slope; Paris; Hybride; EUR 55 000 - 80 000; Plein temps

Avantages offerts par ce poste

Paid time off

Comprehensive medical insurance

Team off-sites

Covered subscriptions for AI tools

Résumé du poste

Slope is looking for a research engineer in Paris to build and maintain benchmarks covering AI safety and model capabilities. The ideal candidate will own the internal benchmark suite and work closely with the product team on research projects.

Qualifications include experience in building LLM benchmarks and a solid understanding of AI safety. This position offers a hybrid work model with comprehensive medical insurance.

Qualifications

• Experience building LLM benchmarks for specific model capabilities.
• Proficient in Python programming, capable of writing maintainable code.
• Understanding of AI safety and evaluation methodologies.

Responsabilités

• Own and maintain internal benchmark suite.
• Build benchmarks and evals for product team.
• Research agentic failure modes in the wild.

Connaissances

Benchmark creation

Python programming

AI safety knowledge

Agentic scaffold experience

Description du poste

Slope is looking for a research engineer in Paris to build and maintain benchmarks covering AI safety and model capabilities. The ideal candidate will own the internal benchmark suite and work closely with the product team on research projects.

Qualifications include experience in building LLM benchmarks and a solid understanding of AI safety. This position offers a hybrid work model with comprehensive medical insurance.