Research Engineer / Scientist, Alignment Science (London)
Description For Research Engineer / Scientist, Alignment Science (London)
Anthropic is seeking a Research Engineer / Scientist for their Alignment Science team in London. The role involves building and running machine learning experiments to understand and steer the behavior of powerful AI systems. Key responsibilities include testing safety techniques, running multi-agent reinforcement learning experiments, building tooling for LLM jailbreak evaluations, and contributing to research papers. The ideal candidate has software and ML experience, familiarity with AI safety research, and a collaborative mindset. Strong candidates may have experience with LLMs, reinforcement learning, and complex codebases. The role offers competitive compensation, equity, and benefits, with a focus on making AI helpful, honest, and harmless.
Responsibilities For Research Engineer / Scientist, Alignment Science (London)
- Build and run machine learning experiments to understand and steer AI behavior
- Test robustness of safety techniques
- Run multi-agent reinforcement learning experiments
- Build tooling for LLM jailbreak evaluations
- Write scripts and prompts for model evaluation
- Contribute to research papers, blog posts, and talks
- Run experiments for key AI safety efforts
Requirements For Research Engineer / Scientist, Alignment Science (London)
- Significant software, ML, or research engineering experience
- Experience contributing to empirical AI research projects
- Familiarity with technical AI safety research
- Preference for fast-moving collaborative projects
- Willingness to pick up slack outside job description
- Care about the impacts of AI
Benefits For Research Engineer / Scientist, Alignment Science (London)
- Equity
- Health insurance
- Dental insurance
- Vision insurance
- 401k with 4% matching
- 22 weeks paid parental leave
- Unlimited PTO
- Education stipend
- Wellness stipend
- Fertility benefits
- Daily lunches and snacks
- Relocation support
