AI Security & Control Researcher

AI Security & Control Researcher Overview

Apollo Research is seeking an AI Security & Control Researcher to join our team in London or San Francisco. This role involves working closely with leading AI companies to enhance the security of AI models and systems. As a key contributor, you will have the opportunity to shape the direction of your role and potentially take on management responsibilities in the future.

Key Responsibilities

• Develop threat models for coding agents, focusing on both immediate and long-term risks such as data leaks and sabotage of safety research.
• Analyze coding agents as potential insider threats, mapping out attack progressions and kill chains using frameworks like MITRE ATT&CK.
• Establish and maintain ‘coding agent security levels’ to define the robustness of the Watcher product against various failure modes.
• Maintain a comprehensive library of coding agent failure modes, ensuring it reflects current academic and industry literature.
• Design realistic attack scenarios and exploits for monitor development and backtesting, collaborating with the research team to validate monitors against adversarial behavior.
• Act as a security adjudicator for flagged agent behaviors, determining the nature of the behavior and providing feedback for monitor enhancements.
• Conduct red-teaming exercises on Watcher, documenting findings and integrating them into product improvements.

Job Requirements

• 5+ years of experience in security roles with a hands-on technical focus.
• Ability to think critically about threat modeling and failure modes, with proficiency in reading code and evaluating technical controls.
• Direct experience in security research, threat modeling, or offensive security.
• Comfortable working in a dynamic, fast-paced environment and managing ambiguous research questions independently.
• Strong written communication skills for producing clear and precise documentation related to threat models and security protocols.

Benefits

• Competitive salary and equity options.
• Salary range: $204,000 – $385,000 in San Francisco; £136,000 – £258,000 in London, with plans for salary increases.
• Flexible working hours and arrangements.
• Unlimited vacation and sick leave.
• Up to 6 months of paid parental leave.
• Comprehensive health, dental, and vision insurance.
• Retirement savings plan with competitive employer matching.
• Free meals including lunch, dinner, and snacks on workdays.
• Paid work-related trips and conferences.
• Annual professional development budget of $1,000.
• Relocation support and assistance with visa fees, if applicable.

Working Pattern

This is an onsite role based in either our London or San Francisco office, with flexible working hours available.

Visa Sponsorship

We sponsor visas in both the UK and US. Sponsorship isn’t guaranteed for every role or candidate, but if we make you an offer, we’ll work with you to find the right visa route.

How to Apply

Please complete the application form with your CV. A cover letter is not required. Feel free to include links to relevant work samples. Our interview process includes a screening interview, a take-home test, technical interviews, and a final interview with the CEO.

Degree Requirement: Not Specified

Visa Sponsorship Promising