Research Engineer — AI Safety Benchmarks & Guardrails

White Circle; Paris; Hybride; EUR 131 371 - 218 952; Plein temps

Avantages offerts par ce poste

Paid time off

Comprehensive medical insurance

Team off-sites twice a year

Résumé du poste

White Circle is looking for a research engineer in Paris to build and maintain benchmarks for AI safety. You will own and improve our internal benchmark suite, focusing on agent behaviors and capabilities.

The ideal candidate has experience in developing benchmarks, is proficient in Python, and understands AI safety principles. The role offers hybrid work options and a competitive salary ranging from $150K to $250K.

Qualifications

• Experience in building and maintaining LLM benchmarks.
• Proficiency in Python for production code.
• Familiarity with AI safety models and benchmarks.

Responsabilités

• Own and maintain internal benchmark suite for agentic safety.
• Build and adapt benchmarks for new features.
• Work on research projects quantifying LLM failure modes.

Connaissances

Building LLM benchmarks

Python programming

AI knowledge

Efficient LLM inference setups

Description du poste

White Circle is looking for a research engineer in Paris to build and maintain benchmarks for AI safety. You will own and improve our internal benchmark suite, focusing on agent behaviors and capabilities.

The ideal candidate has experience in developing benchmarks, is proficient in Python, and understands AI safety principles. The role offers hybrid work options and a competitive salary ranging from $150K to $250K.