{"id":463161,"url":"https://alion.io/job/apollo-research-ai-security-control-researcher","title":"AI Security & Control Researcher","company":{"id":178413,"name":"Apollo Research","domain":"apolloresearch.ai","url":"https://alion.io/company/apollo-research","size_band":"51-200","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Lever","truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":"senior","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["London, United Kingdom"],"countries":["GB"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":204000,"max":385000,"currency":"USD","period":"year","gross":null,"usd_annual":385000},"salary_estimate":null,"experience_years_min":5,"visa_sponsorship":true,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"Anthropic","optional":false},{"name":"MITRE ATT&CK","optional":false},{"name":"OpenAI","optional":false},{"name":"Red Teaming","optional":false},{"name":"Threat Modeling","optional":false},{"name":"LLM","optional":true}],"status":"live","first_seen_at":"2026-09-01T08:38:06Z","employer_posted_date":"2026-09-01","last_verified_at":"2026-10-28T20:47:48Z","board_verified":true,"closed_at":null,"days_open":57,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":57},"description":"THE OPPORTUNITY\nTHE OPPORTUNITY\nApollo 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 enterprises.\nWe are looking for a security & control expert to help us design better threat models and control protocols against AI adversaries, and improve the effectiveness and security of Watcher.\nThis is truly a \"start-up role\" in the sense that you have significant say in shaping the direction of the role. This is an individual contributor role but could lead to management responsibilities eventually, if desired.\nKEY RESPONSIBILITIES\nThreat modeling for coding agents\nDevelop threat models for coding agents under the assumption that they could be misaligned or compromised. This includes near-term threats like AI agents leaking private internal data and long-term threats like agents sabotaging safety research.\n\nTreat coding agents through the lens of insider risk: they have credentials, access to code, network access, and the ability to execute arbitrary actions, just like a malicious insider would (see Control agenda).\n\nMap out kill chains and attack progressions similar to frameworks like MITRE ATT&CK, adapted for agentic AI. See e.g. the Agentic Loss-of-Control Threat Matrix for an example of a high-quality contribution.\n\nBuild and maintain our “coding agent security levels” which define what level of robustness Watcher provides against different categories of failure modes. These levels should be concrete, testable, and usable both internally (to guide product priorities) and externally (to communicate our security posture to customers).\n\nFailure mode library and literature\nMaintain our library of coding agent failure modes and keep it comprehensive, accurate, and current.\n\nStay up to date with the academic and industry literature on coding agent security, AI security, and adjacent fields (prompt injection, deception, accidental security implications, supply chain attacks on AI systems, etc.).\n\nAttack design for monitor development\nDesign realistic attack trajectories and example exploits for monitor development and backtesting, work with the research team to ensure monitors are trained and evaluated against credible adversarial behavior.\n\nTrajectory adjudication\nServe as security adjudicator for flagged trajectories. When monitors flag ambiguous agent behavior, determine whether it represents a genuine attack, a benign-but-unusual workflow, or needs deeper investigation, and feed those judgments back into monitor improvement.\n\nRed-teaming Watcher\nRed-team and improve Watcher's monitors and policies, document findings, and feed them into product improvement.\n\nWork with the technical research staff to build adversarial test suites into the backtesting pipeline.\n\n*This role is distinct from the AI Security Researcher role on Apollo's Infra & Security team, which threat-models Apollo's own internal systems and the agents operating on them.\nREPRESENTATIVE PROJECTS\nDevelop a comprehensive coding agent threat model: Think deeply about all the ways in which coding agents could attack an organization. Compare this threat model to conventional threats from human insiders. Publish a detailed research piece describing the threat model building on existing research, e.g. from Redwood Research.\n\nImprove our database of failure modes: We have an internal database of 50+ failure modes of coding agents with detailed reports for all of them. For this project, you would provide an expert view on the current state of that database and suggest improvements. In the long run, you would maintain that database and be responsible for integration of new failures.\n\nPrioritize failure modes that Watcher should cover: Different parts of Watcher attempt to cover different threat models and attack strategies. Based on the results of the threat model project above, we want to ensure that each part of Watcher covers the most important failure modes in the most efficient way. For example, not all monitors require blocking capability and some failure modes might benefit from additional affordances like being able to disperse subagents.\n\nJOB REQUIREMENTS\nMust-haves\n 5+ years in security roles in a hands-on technical capacity (not purely GRC/compliance). You need to be able to think structurally about threat modeling and failure modes. You need to be able to read code, understand infrastructure, and evaluate technical controls, not just write policies.\nDirect experience with security research, threat modeling, or offensive security.\nComfortable working in a small, fast-moving team, and comfortable owning ambiguous, open-ended research questions.\nStrong written communication this role produces threat models, security levels, and failure mode documentation that need to be clear and precise\nNice-to-haves\nExperience with AI/ML systems security, LLM security, or AI control research. The field is young enough that deep experience here is rare, but any exposure significantly reduces ramp-up time.\n\nDetection engineering, SOC, or incident analysis experience. A part of this role is judging whether flagged agent behavior is genuinely malicious, and people who have triaged real-world alerts might ramp much faster.\n\nFamiliarity with insider threat programs or insider risk frameworks. The mental model of \"the coding agent is a potentially malicious insider\" is useful for this role and someone who has worked on insider threats will pick it up faster.\n\nRed teaming or offensive security background. Useful for the Watcher red-teaming responsibilities and for thinking adversarially about failure modes.\n\nFormal AI safety research background. Helpful but not necessary. We need security practitioners who can learn the AI safety context, not AI safety researchers who need to learn security.\n\nExplicitly not required\nManagement experience. This is an IC role, at least initially.\n\nSpecific certifications (CISSP, etc.). We care about demonstrated ability, not credentials.\n\nWe want to emphasize that people who feel they don’t fulfill all of these characteristics but think they would be a good fit for the position, nonetheless, are strongly encouraged to apply.\nBENEFITS\nThis role offers market competitive salary, equity, and competitive benefits.\nSalary: San Francisco: $204,000 - $385,000; London: £136,000 - £258,000. We will be looking to meaningfully raise salaries soon. \nFlexible work hours and schedule\nUnlimited vacation\nUnlimited sick leave\nUp to 6 months of paid parental leave\nComprehensive health, dental and vision insurance\nRetirement savings with competitive employer matching (e.g. 401(k) for US employees)\nLunch, dinner, and snacks are provided for all employees on workdays\nPaid work trips, including staff retreats, business trips, and relevant conferences\nA yearly $1,000 (USD) professional development budget\nRelocation support and visa fees (if applicable) \nLOGISTICS\nTime Allocation: Full-time\nLocation: This is an in-person role working out of our London or San Francisco office. We offer flexible working hours and some wfh arrangements. \n 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.","description_format":"text","description_chars":7531,"description_truncated":false,"requirements":{"experience_years_min":5,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":["Equity","Flexible schedule","Parental leave","Professional development","Vision insurance"],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":true,"industries":["AI Safety & Alignment"],"lifecycle":[{"event":"open","at":"2026-09-06T11:37:30Z"}],"visa":[{"country":"GB","licensed_sponsor":true,"evidence":"Licensed UK visa sponsor (Skilled Worker, Senior or Specialist Worker)","filings_12m":null,"filings_prev_12m":null,"green_card_filings_12m":null,"median_offered_wage_usd":null,"route":"Skilled Worker; Global Business Mobility: Senior or Specialist Worker","cap_exempt":false,"checked_at":"2026-10-28T06:26:45+00:00","sources":["UK Home Office: register of licensed sponsors (workers)"],"filings_for_role_12m":0}],"liveness":{"score":28,"band":"fade","label":"Fading","p_open":1,"p_active":0.617,"p_room":0.45,"age_days":56,"expected_fill_days":36,"reasons":["conf:3","win:tail"],"computed_at":"2026-10-28T05:59:10Z"},"pay":{"stated_usd_annual":385000,"is_top_pay":true},"html_url":"https://alion.io/job/apollo-research-ai-security-control-researcher","json_url":"https://alion.io/job/apollo-research-ai-security-control-researcher.json","meta":{"generated_at":"2026-10-28T21:27:59Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":29624,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-29T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":178413},"rest":"https://alion.io/mcp/rest/get_company?id=178413"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fapollo-research-ai-security-control-researcher"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Fapollo-research-ai-security-control-researcher"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Fapollo-research-ai-security-control-researcher"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/apollo-research-ai-security-control-researcher\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fapollo-research-ai-security-control-researcher"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":463161}},{"tool":"search_jobs","arguments":{"company":"apolloresearch.ai","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":463161},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}