Clash
of Jobs
Browse All Jobs
Job Description
Anthropic is seeking a Research Engineer/Scientist to join their Alignment Science team in London. This role focuses on understanding and steering the behavior of powerful AI systems, ensuring they are helpful, honest, and harmless. The ideal candidate will blend scientific rigor with engineering expertise, contributing to exploratory research on AI safety, particularly concerning risks from advanced AI systems. The role involves collaboration with teams like Interpretability, Fine-Tuning, and the Frontier Red Team.
Role Involves:
- Building and running machine learning experiments.
- Testing the robustness of safety techniques.
- Running multi-agent reinforcement learning experiments.
- Building tooling to evaluate LLM-generated jailbreaks.
- Writing scripts and prompts for evaluation questions.
- Contributing to research papers, blog posts, and talks.
- Running experiments for AI safety efforts.
Requirements:
- Significant software, ML, or research engineering experience.
- Experience contributing to empirical AI research projects.
- Familiarity with technical AI safety research.
- Ability to work in fast-moving collaborative projects.
- Care about the impacts of AI.
- Bachelor's degree in a related field or equivalent experience.
What Anthropic Offers:
- Competitive compensation and benefits.
- Optional equity donation matching.
- Generous vacation and parental leave.
- Flexible working hours.
