[Expression of Interest] Research Engineer / Scientist, Alignment - London
Anthropic · London, UK
CHECKED 3H AGO
Frontier labonsite$344k–$490k
At a glance
Highlights
- Run elegant ML experiments to understand and steer powerful AI systems.
- Advance AI Control and alignment stress-testing with model organisms.
- Test safety robustness via debate, red-teaming and jailbreak evaluations.
What they offer
- Competitive compensation and benefits
- Optional equity donation matching
- Generous vacation and parental leave
- Flexible working hours
- Collaborative office space
Ideal candidate
Collaborative scientist-engineer passionate about safe, beneficial AI who thrives in fast-moving team experiments and jumps in wherever needed to understand powerful systems.
Requirements
- Significant software, ML, or research engineering experience
- Experience contributing to empirical AI research projects
- Familiarity with technical AI safety research
- Bachelor's degree or equivalent in a relevant field
- remote policy
- Hybrid - in office at least 25% of the time
- visa sponsorship
- Sponsors visas where possible with immigration lawyer support
- hiring process
- All interviews conducted in Python
Lab profile
About Anthropic
AI safety company building reliable, interpretable and steerable frontier AI systems.
What they build
- Claude
- Claude API
- Claude Code
Known for
- AI safety and alignment
- Model interpretability research
- Frontier LLM development
Key facts
- Founded in 2021
- Headquartered in San Francisco, California
- Backed by Amazon and Google