Search
Go
Research Scientist/Engineer (Evaluations)
GREATER LONDON · GB
—
Full-time
About the Role
Apollo Research is seeking a Research Scientist/Engineer to join its AI evaluation team. The role focuses on frontier AI, AI safety, and machine learning evaluation, with an emphasis on large language models (LLMs). You will contribute to the development of evaluation methods and work on ensuring the safety and robustness of AI systems.
Responsibilities
- Develop and implement evaluation protocols for frontier AI systems
- Focus on AI safety and robustness of large language models
- Collaborate with a team on machine learning evaluation methods
Requirements
- Background in machine learning and large language models
- Experience with AI evaluation or model assessment
- Strong programming and analytical skills
Nice to Have
- Experience in AI safety research
- Familiarity with evaluation benchmarks
Tech Stack
LLM
AR
Apollo Research
Greater London · GB · 28+ employees
Apollo Research is a public benefit corporation focused on AI safety, specifically conducting fundamental research into the science of scheming in frontier AI systems to prevent harmful, misaligned behaviors. They also develop monitoring tools and advise on technical AI governance.
