Cyber Evaluations Engineer
Anthropic · Remote-Friendly, United States; San Francisco, CA | Washington, DC · San Francisco, CA
CHECKED 2H AGO
Frontier labremote$300k–$405k
At a glance
Highlights
- Build and run evals measuring cyber capabilities and safeguard robustness in models.
- Run per-release robustness testing ahead of major model launches to probe safeguards.
- Design probes that detect cyber abuse in production and shape detection architecture.
What they offer
- Competitive compensation and benefits
- Optional equity donation matching
- Generous vacation and parental leave
- Flexible working hours
Ideal candidate
Hands-on security researcher who loves breaking and measuring systems and translating findings into stronger safeguards. Collaborative communicator excited to shape AI safety through rigorous testing and detection work.
Requirements
- Experience building or running evaluations, benchmarks, or test suites for software or ML systems, including delivering results on short, fixed timelines
- Hands-on cybersecurity experience (e.g., CTF participation, vulnerability research, exploit development, or security research)
- Proficiency in Python
- Strong ability to communicate evaluation results with cross-functional and policy stakeholders
- Bachelor's degree or equivalent combination of education, training and/or experience
- remote policy
- Hybrid - expected in office at least 25% of the time
- visa sponsorship
- We sponsor visas but are not able to successfully sponsor every role and candidate
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