Research Engineer (Evals)
Hybrid (Paris), Hybrid (London)Full-timePosted 3mo ago
About the role
Research Engineer to build and maintain internal benchmarks for single/multi-turn content guardrails and agentic safety, and to work on projects studying agent behaviours in the wild.
Responsibilities
- Own and maintain our internal benchmark suite, covering single/multi-turn content guardrails and agentic safety.
Qualifications
- Have built an LLM benchmark from scratch that distinguished specific model capabilities (produced a measurable, defensible capability difference).
- Have 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.
Skills
Required:Benchmark design and implementationSynthetic data generationPython software engineeringLLM inference orchestration
Nice to have:Agentive safety evaluation
Benefits
- Competitive compensation, including equity
- Flexible time off
- Office in central London/Paris with flexible hybrid setup
- Relocation support if you’re moving to Paris, available after your probationary period
- Premium private health insurance
- Mental health support, including coverage for therapy when you need it
- Lunch and dinner covered when you work from the office
- Learning and development support for courses, conferences, and opportunities to grow your skills
- All the hardware, subscriptions, tools, and services you need
- Team off-sites twice a year: Alps, Saint-Tropez, Marbella
Last updated Oct 7, 2026. Interested? Apply on the company site.
About White Circle
We keep your AI models safe, reliable, and secure.
We keep your AI models safe, reliable, and secure.
AI governanceAI safetycase studiescomplianceenterpriseheadline-ai-europe-100-2026model governancepolicy enforcement
More open roles at White Circle
- DevRel Lead (Developer Relations)2w agoRemote · Product
- Communications Designer2w agoRemote · Creative
- Production Manager1mo agoRemote · Creative
- Talent Lead1mo agoRemote · Operations
- Finance Lead1mo agoRemote · Operations