Research Engineer: AI Benchmarks & Guardrails

Whitecircle; Paris; Hybride; EUR 70 000 - 110 000; Plein temps

Avantages offerts par ce poste

Paid time off

Relocation package

Equity

Comprehensive health insurance

Hardware and tools

Subscriptions for AI agents and IDEs

Team off-sites

Résumé du poste

White Circle, an AI Safety company, is seeking a research engineer to build and maintain our internal benchmarks for single/multi-turn content and agentic safety, and to study agent behaviours in the wild. You will also work with the team on projects studying agent behaviours in the wild and advancing safety benchmarks.

You will collaborate with product to build evals for flagship models, extend benchmarks to new features and verticals, and contribute to research on reliability and safety in

Qualifications

• Built an LLM benchmark from scratch that distinguished specific model capabilities.
• Built synthetic data for post-training textual or multimodal models.
• Can reproduce a published benchmark result and identify where the original methodology is fragile or misleading.
• You write Python that other people can build on. Our whole stack is Python; we want someone who has shipped and maintained production code and who factors messy problems into clean abstractions others can extend.
• You can write efficient LLM inference setups, including sensible orchestration of parallel calls, retries, rate-limit handling.
• An AI power-user — fluent with frontier models and coding agents day to day.

Responsabilités

• Own and maintain our internal benchmark suite, covering single/multi-turn content guardrails and agentic safety.
• Build benchmarks that distinguish specific model capabilities.
• Work with the product team to build evals covering core functionality of our flagship models.
• Build benchmarks for new features coming out of the research team.
• Adapt and extend evals to new verticals and changing product data.
• Work on research projects that study and quantify realistic agentic and LLM failure modes in the wild.

Connaissances

Python

LLM benchmarks

Production-grade code

Agentic safety

Experiment design

Data synthesis

Outils

Benchmark frameworks

LLM inference setup

Description du poste

White Circle, an AI Safety company, is seeking a research engineer to build and maintain our internal benchmarks for single/multi-turn content and agentic safety, and to study agent behaviours in the wild. You will also work with the team on projects studying agent behaviours in the wild and advancing safety benchmarks.

You will collaborate with product to build evals for flagship models, extend benchmarks to new features and verticals, and contribute to research on reliability and safety in