AI Security Researcher
Apollo Research2 months ago
London, United Kingdom or San Francisco, CA, USASenior
Base Salary
$214k - $280k/yr
Responsibilities
- Own the security of Apollo’s internal software, infrastructure, AI agent access controls, and monitoring surfaces.
- Red-team internal systems and agent sandboxes, develop realistic attack trajectories, and assess isolation, data exfiltration, and evaluation integrity risks.
- Design solutions for novel AI security threats and establish security standards where existing playbooks do not apply.
- Track adversary tactics, techniques, and campaigns and translate intelligence into tuned, high-signal detections.
- Drive security findings through remediation by building and deploying controls, checks, tests, defaults, detections, and CI/CD integrations.
- Develop comprehensive threat models for coding agents with credentials, code, network, and execution access.
Requirements
- At least 5 years of hands-on technical experience in security roles, excluding purely GRC or compliance work.
- Direct offensive security experience, including threat modeling or red teaming, with application or cloud security knowledge.
- Ability to read code, understand infrastructure, evaluate technical controls, and translate security findings into fixes and scalable automated controls.
- Engineering mindset with experience or aptitude for paved roads, custom detection rules, adversarial test suites, and CI/CD integrations.
- Strong written communication skills for producing clear threat models, reports, and failure-mode documentation.
- Ability to work effectively in a fast-moving startup environment with ambiguity and changing priorities.
- Preferred experience includes AI/ML systems security, LLM security, detection engineering, SOC work, incident analysis, insider-threat programs, or insider-risk frameworks.
- Formal AI safety research experience is explicitly not required.
Benefits
- Full-time, in-person role based in the London or San Francisco office, with flexible working hours and some work-from-home arrangements.
- Visa sponsorship is available in both the UK and US, subject to the company’s ability to find an appropriate visa route after an offer.
- Equity and competitive benefits are offered.
- Flexible work hours and schedule, unlimited vacation, and unlimited sick leave.
- Up to 6 months of paid parental leave and comprehensive health, dental, and vision insurance.
- Retirement savings with competitive employer matching, including 401(k) for US employees.
- Lunch, dinner, and snacks provided on workdays.
- Paid work trips, including retreats, business trips, and relevant conferences.
- Annual $1,000 USD professional development budget.
- Relocation support and visa fees if applicable.
Categories
About Apollo Research
Apollo Research evaluates and stress-tests frontier AI models for safety risks and builds security tools for agentic systems used by enterprise engineering teams. It works with OpenAI, Anthropic, Google, Meta and others to run pre-deployment tests focused on deceptive behavior and loss-of-control risks, and sells Watcher, a coding-agent security product that monitors billions of tokens in production. Revenue comes from enterprise software and research partnerships with AI labs and agent-building companies.