--- title: 'AI Security Researcher at Apollo Research' canonical: 'https://feeny.ai/job/ai-security-researcher-apollo-research-london-wk1vfhdtjh9h' type: 'job' last_seen: '2026-09-08' --- # AI Security Researcher at Apollo Research - **Company:** Apollo Research - **Location:** London, United Kingdom / San Francisco, CA - **Employment:** full-time - **Work type:** onsite - **Posted:** 2026-08-28 - **Last confirmed live:** 2026-09-08 - **Apply:** https://jobs.lever.co/apolloresearch/8c19d363-a4b1-4207-b5de-24d2d2267c64 ## Job description ## THE OPPORTUNITY Apollo Research works with most frontier AI companies (OpenAI, Anthropic, Google, Meta, Thinking Machines and others) to test their models before deployment and collaborate on fundamental scheming research. Our coding agent security product, Watcher, is deployed in production and monitors billions of agent tokens per month across engineering teams at agent-building scale-ups and enterprise. Security exists at Apollo to safeguard the trust frontier labs place in us and to enable that research. Our own team uses AI agents extensively across its work, which makes Apollo both a target and a testbed. We’re hiring AI Security Researchers to join the Infra & Security Team. In this role, you will identify, research and remediate both conventional threats and the novel risks introduced by AI agents that can affect Apollo and our mission. You will redefine and work on a new class of insider risk that didn’t exist before. ## RESPONSIBILITIES - Hold responsibility for the security of Apollo’s internal surfaces. Red-team internal software, infrastructure, and AI agent access controls/monitoring. Build realistic attack trajectories. - Design solutions for novel or emerging threats in the AI security space, where no existing playbook applies. Set the standard for our security posture in these areas. - Track adversary tactics, techniques, and campaigns relevant to Apollo's threat landscape, and translate that intelligence into tuned, high-signal detections. - Own each finding through to a deployed fix. Build and roll out durable controls: checks, tests, defaults, detections. Socialise them, work with engineers to implement, and hold remediation to a high bar. ## KEY REQUIREMENTS Must haves - 5+ years in security roles in a hands-on technical capacity (not purely GRC/compliance). You'd need to be able to think structurally about threat modelling and failure modes. You need to be able to read code, understand infrastructure, and evaluate technical controls. - Direct experience with offensive security. Threat modelling, red teaming, etc. Knowledge of application or cloud. Ideally you owned or significantly contributed to the security posture of an organisation or product that handles sensitive customer data. - Engineering mindset. You treat security as an engineering problem. You can translate your findings into fixes and controls, such as paved roads, custom detection rules, adversarial test suites, CI/CD integrations. You prioritize automation and systems-level thinking to scale security, and you are comfortable leveraging AI to accelerate development. - Startup pace. You are excited about a fast-moving environment, comfortable with ambiguity and changing priorities, and willing to grind when it matters. - Strong written communication. This role produces a lot of artifacts (threat models, reports, failure mode documentation) and they need to be clear and precise. Nice to haves - Experience with AI/ML systems security or LLM security. - Detection engineering, SOC, or incident analysis experience. - Familiarity with insider threat programs or insider risk frameworks. Explicitly not required - Formal AI safety research background. We need security practitioners who can learn the AI safety context, not AI safety researchers who need to learn security. ## REPRESENTATIVE PROJECTS - Red-team Apollo's agent sandboxes used for evals: Test whether an agent can escape isolation, exfiltrate data, detect it's being evaluated, or otherwise undermine the validity of eval results. Your findings will harden the sandbox infrastructure the research team depends on to trust its own eval results. - Comprehensive coding agent threat model: Map every way a coding agent with internal access: credentials, code, network, execution ability,  could attack Apollo, benchmarked against what a human insider with the same access could do. ## BENEFITS - This role offers market competitive salary, equity, and competitive benefits. - Salary: San Francisco: $214,000 – $280,000; London: £144,000 – £189,000. We will be looking to meaningfully raise salaries soon. - Our engineers effectively have an unlimited token budget. If a better result costs more compute, use it. - Flexible work hours and schedule - Unlimited vacation - Unlimited sick leave - Up to 6 months of paid parental leave - Comprehensive health, dental and vision insurance - Retirement savings with competitive employer matching (e.g. 401(k) for US employees) - Lunch, dinner, and snacks are provided for all employees on workdays - Paid work trips, including staff retreats, business trips, and relevant conferences - A yearly $1,000 (USD) professional development budget - Relocation support and visa fees (if applicable) ## LOGISTICS - Time Allocation: Full-time - Location: This is an in-person role working out of our London or San Francisco office. We offer flexible working hours and some wfh arrangements. - 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. ## ABOUT THE TEAM The Infra and Security team is currently led by Rusheb Shah and consists of Glen Rodgers and Steven Lee. You will work closely with Security Engineers we’re hiring for as well as technical staff from the Scheming Research and Product team. You can find our full team here. ## ABOUT APOLLO RESEARCH The rapid rise in AI capabilities offers tremendous opportunities, but also presents significant risks. At Apollo Research, we're primarily concerned with risks from Loss of Control, i.e. risks coming from the model itself rather than e.g. humans misusing the AI. We're particularly concerned with deceptive alignment / scheming, a phenomenon where a model appears to be aligned but is, in fact, misaligned and capable of evading human oversight. We work on the science of scheming, detection of scheming (e.g. building evaluations), and scheming mitigations (e.g. anti-scheming). We also work on control and monitoring research (see our scalable monitoring agenda). We work closely with many frontier AI companies, such as OpenAI, Anthropic, Google, Meta, Thinking Machines and others, e.g. to test their models and collaborate on the science of scheming. At Apollo, we aim for a culture that emphasizes truth-seeking, being goal-oriented, giving and receiving constructive feedback, and being friendly and helpful. If you're interested in more details about what it's like working at Apollo, you can find more information here. We also build a coding agent security product called Watcher that secures agent deployments in companies. Our goal is to reduce the probability of catastrophic incidents by securing coding agents, learning about their real-world risks, and publishing our research on how to build these control systems most effectively. Equality Statement: Apollo Research is an Equal Opportunity Employer. We value diversity and are committed to providing equal opportunities to all, regardless of age, disability, gender reassignment, marriage and civil partnership, pregnancy and maternity, race, religion or belief, sex, or sexual orientation. ## HOW TO APPLY Please complete the application form with your CV. The provision of a cover letter is neither required nor encouraged. Please also feel free to share links to relevant work samples. About the interview process: Our multi-stage process includes a screening interview, a take-home test (approx. 2-3 hours), 3 technical interviews, and a final interview with Marius (CEO). There are no leetcode-style general coding interviews. You may use AI tools on the take-home; we judge the result the way we'd judge any contributor's work, so you are responsible for the quality of everything you submit. Your Privacy and Fairness in Our Recruitment Process: We are committed to protecting your data, ensuring fairness, and adhering to workplace fairness principles in our recruitment process. To enhance hiring efficiency, we use AI-powered tools to assist with tasks such as resume screening. These tools are designed and deployed in compliance with internationally recognized AI governance frameworks. Your personal data is handled securely and transparently. All resumes are screened by a human and final hiring decisions are made by our team. If you have questions about how your data is processed or wish to report concerns about fairness, please contact us at info@apolloresearch.ai. ## About Apollo Research ## Company Overview - **One-liner**: Apollo Research is an AI safety organization dedicated to securing frontier AI systems by detecting and preventing scheming (deceptive alignment) through technical research, evaluations, monitoring products, and policy guidance. - **Entity Type**: Private (Public Benefit Corporation) - **Headquarters**: London, United Kingdom (with offices in San Francisco, California, and opening Washington, D.C.) - **Founded**: 2023 - **Founders**: Not publicly available from sources ## Core Business - **Primary industry**: AI safety research and assurance; security monitoring for AI agents - **Target customers**: Frontier AI developers (e.g., OpenAI, major labs), governments and international bodies, enterprises deploying AI agents - **Mission**: "Secure frontier AI systems across development, deployment, and governance" [apolloresearch.ai/about](https://www.apolloresearch.ai/about) ## Products & Services - **Scheming Evaluations**: Behavioral and interpretability-based evaluations to detect whether frontier AI models exhibit deceptive alignment (scheming). Apollo runs these evaluations in partnership with major AI labs, including OpenAI, to assess models before public deployment. [apolloresearch.ai/about](https://www.apolloresearch.ai/about) - **Watcher (Monitoring Product)**: A two-part product for controlling and securing coding agent deployments: - *Watcher Live* – Real-time monitor that identifies and blocks undesirable actions or steers agents back on track. - *Watcher Analyze* – Observability layer for reviewing all agent activity, analyzing failures, and receiving notifications. [apolloresearch.ai/blog](https://apolloresearch.ai/blog/apollo-update-may-2026) - **Governance Advisory & Policy Playbooks**: Threat modeling, loss‑of‑control playbooks, and policy recommendations for governments (e.g., EU AI Office, US Congress, UN Advisory Body). Notable outputs include *The Loss of Control Playbook* and the *Behind Closed Doors* primer on internal deployment. [apolloresearch.ai/blog](https://apolloresearch.ai/blog/apollo-update-may-2026) ## Market Standing - **Valuation**: Not publicly available - **Key Metric**: Headcount of 28 employees (as of mid‑2026), growing 72% year‑over‑year [linkedin.com](https://linkedin.com/company/apollo-research-ai) - **Notable Investors/Partners**: OpenAI (partnered for testing o1 and anti‑scheming interventions), EU AI Office, UN Advisory Body, US Congress [apolloresearch.ai/about](https://www.apolloresearch.ai/about) - **Growth Signals**: Opened San Francisco office in 2026 with plans to grow to 10+ staff; opening Washington, D.C. office in June 2026; expanding from evals into a full “Science of Scheming” research agenda and a commercial monitoring product [apolloresearch.ai/blog](https://apolloresearch.ai/blog/apollo-update-may-2026) ## Competitive Advantages - **Unique focus on “scheming”**: Apollo is one of the few organizations dedicated specifically to detecting and preventing deceptive alignment—a risk many labs now acknowledge. - **First-mover evidence**: Published the first public evidence that frontier models can scheme in context, lending credibility and urgency to their work. - **Deep lab partnerships**: Direct collaborations with frontier AI developers (e.g., OpenAI) allow Apollo to run pre‑deployment evaluations and influence safety practices. - **Dual research‑product model**: Combining fundamental behavioral research with a commercial monitoring product (Watcher) creates a real‑world feedback loop and diversified funding. ## Strategic Focus - **Science of Scheming**: Understanding how scaling trends (e.g., increased situational awareness, long‑horizon RL) drive scheming behavior in future models, rather than only evaluating current models. - **Evaluation campaigns**: Running suites of behavioral and interpretability tests across frontier models to generalize findings from individual systems. - **Monitoring productization**: Scaling Watcher as an enterprise tool for securing coding agents, with both immediate safety and long‑term oversight subversion use cases. - **Policy influence**: Advising governments on loss‑of‑control, internal deployment, and automated AI R&D risks; establishing a D.C. presence to shape national security procurement and regulation. ## Why Work Here - **Mission‑driven**: Employees work directly on preventing one of the most severe risks from advanced AI—scheming and loss‑of‑control [apolloresearch.ai/careers](https://www.apolloresearch.ai/careers). - **Compensation**: Competitive salary, equity, pension/401(k) matching, visa sponsorship, and relocation support [apolloresearch.ai/careers](https://www.apolloresearch.ai/careers). - **Culture**: In‑person collaborative culture with offices in London, San Francisco, and D.C. – “the best collaboration happens in person,” though flexible working hours and work‑from‑home days are offered [apolloresearch.ai/careers](https://www.apolloresearch.ai/careers). - **AI‑native engineering**: Fluency with AI tools and coding agents is valued; the company expects an engineering mindset and real‑world production skills. - **High impact**: Small, fast‑growing team (28 people) with outsized influence on frontier AI policy and lab safety practices. ## Sources 1. [apolloresearch.ai/about](https://www.apolloresearch.ai/about) 2. [apolloresearch.ai/careers](https://www.apolloresearch.ai/careers) 3. [linkedin.com](https://linkedin.com/company/apollo-research-ai) 4. [apolloresearch.ai/team](https://www.apolloresearch.ai/team) 5. [apolloresearch.ai/blog](https://apolloresearch.ai/blog/apollo-update-may-2026) ## Other roles at Apollo Research - [Product Security Engineer](https://feeny.ai/job/product-security-engineer-apollo-research-london-h1258hfrypcz) — London, United Kingdom / San Francisco, CA - [AI Security & Control Researcher](https://feeny.ai/job/ai-security-control-researcher-apollo-research-london-beb9je2z6pn8) — London, United Kingdom / San Francisco, CA - [AI Red Team Engineer](https://feeny.ai/job/ai-red-team-engineer-apollo-research-london-b1srz25aayap) — London, United Kingdom / San Francisco, CA - [Research Scientist (Control)](https://feeny.ai/job/research-scientist-control-apollo-research-london-rp39n348emvs) — London, United Kingdom / San Francisco, CA - [Security Engineer](https://feeny.ai/job/security-engineer-apollo-research-london-53m9rf98tb82) — London, United Kingdom / San Francisco, CA - [Forward Deployed Engineer (Product)](https://feeny.ai/job/forward-deployed-engineer-product-apollo-research-london-yjdd40mmbgex) — London, United Kingdom / San Francisco, CA - [Engineering Manager (Product)](https://feeny.ai/job/engineering-manager-product-apollo-research-london-jtv0gj1629tb) — London, United Kingdom / San Francisco, CA - [Full-stack Software Engineer (Product)](https://feeny.ai/job/full-stack-software-engineer-product-apollo-research-london-d2xch3vq5scw) — London, United Kingdom / San Francisco, CA - [Finance Associate (Expression of Interest)](https://feeny.ai/job/finance-associate-expression-of-interest-apollo-research-london-4swgyne5je2z) — London, United Kingdom - [Senior Security Engineer](https://feeny.ai/job/senior-security-engineer-apollo-research-london-t3etvam53yfq) — London, United Kingdom