Researcher, Frontier Robustness
Posted Updated
Description
You will develop and test new methods for securing frontier AI systems, designing experiments with frontier models, building threat models and adversarial tests, and prototyping defenses. You will write code and tools, red-team model-based safeguards and monitors, and work with Security and infrastructure teams to deploy protections. The role is based in San Francisco.
Responsibilities
- Design and run experiments using frontier models to discover failure modes in sandboxes and research infrastructure
- Develop threat models and novel adversarial tests
- Invent, prototype and evaluate defenses that strengthen isolation
- Develop and red-team model-based safeguards and monitors
- Develop automated adversarial tests and repeatable evaluations
- Partner across Research, Security and infrastructure teams to deploy improvements
Requirements
- Hands-on experience conducting research with large language models
- Ability to turn open-ended questions into hypotheses and reproducible experiments
- Ability to design rigorous evaluations
- Write and debug code independently
- Practical security experience such as sandboxing, vulnerability research, adversarial testing or detection and monitoring
Benefits
- Equity
- Performance-related bonus
- Medical, dental and vision insurance with HSA employer contributions
- Health FSA, Dependent Care FSA and commuter pre-tax accounts
- 401(k) with employer match
- Paid parental leave, medical and caregiver leave
- Flexible PTO
- 13+ paid company holidays and company office closures
- Mental health and wellness support
- Employer-paid basic life and disability coverage
- Annual learning and development stipend
- Daily meals in offices and meal delivery credits
- Relocation support
- Charitable donation matching and wellness stipends
Skills
Sign in to read and join the discussion.