Research Engineer Scientist Alignment
AI safety and research company building reliable, interpretable, and steerable AI systems, including the Claude product family and developer platform.
Maintainer signals as of 9/23/2026
Funding history
About Anthropic
Anthropic PBC develops frontier AI systems and deploys them through Claude products and the Claude Platform, with a stated focus on safety, interpretability, and steerability.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will conduct exploratory AI safety research and machine-learning experiments. You will test safety techniques, run multi-agent reinforcement-learning experiments, build evaluation tooling, create safety-relevant evaluation prompts, and contribute to research publications and talks.
Requirements
- Software, machine learning, or research engineering experience
- Experience contributing to empirical AI research
- Familiarity with technical AI safety research
- Python interview proficiency
- Bachelor’s degree or equivalent education, training, and/or experience
Responsibilities
- Test the robustness of safety techniques
- Run multi-agent reinforcement-learning experiments
- Build tooling to evaluate LLM-generated jailbreaks
- Write scripts and prompts for safety-relevant reasoning evaluations
- Contribute to research papers, blog posts, and talks
- Run experiments supporting AI safety and responsible scaling efforts
Benefits
- Equity donation matching
- Generous vacation
- Parental leave
- Flexible working hours
Hiring Process
All interviews are conducted in Python.