{"id":463163,"url":"https://alion.io/job/apollo-research-research-scientist-control","title":"Research Scientist (Control)","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":"junior","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":2,"visa_sponsorship":true,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Fine-tuning","optional":false},{"name":"LLM","optional":false},{"name":"Python","optional":false},{"name":"SQL","optional":true}],"status":"live","first_seen_at":"2026-09-01T08:31:40Z","employer_posted_date":"2026-09-01","last_verified_at":"2026-10-27T17:49:21Z","board_verified":true,"closed_at":null,"days_open":56,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":56},"description":"THE OPPORTUNITY\nJoin our new AGI safety product team and help transform AI control research into practical tools that directly reduce risks from AI. As an Research Scientist (Control), you’ll work closely with Marius (CEO & currently leads the monitoring efforts), other control researchers and product engineers.\nWe are currently buildingWatcher, a monitoring tool for coding agents. Ourmonitoring research agenda attempts to translate compute into safety at scale. You will join a small team and will have significant ability to shape the team & tech, and have the ability to earn responsibility quickly.\nYou will like this opportunity if you're passionate about using empirical research to make AI systems safer in practice. You enjoy the challenge of translating theoretical AI risks into concrete detection mechanisms. You thrive on rapid iteration and learning from data. You want your research to directly impact real-world AI safety.\nKEY RESPONSIBILITIES\nTLDR: you will design & implement control protocols (see e.g.[Greenblatt et al, 2023]) and test them on real-world production systems at scale.\nResearch & Development\nDesign and conduct experiments to test monitor effectiveness across different failure modes and agent behaviors\n\nBuild and maintain evaluation frameworks to measure progress on monitoring capabilities\n\nBuild and maintain high-quality datasets to train and test monitors on\n\nIterate on monitoring approaches based on empirical results, balancing detection accuracy with computational efficiency\n\nContribute newly discovered coding agent failure modes to Apollo's shared failure mode library (owned by the AI Security & Control Researcher/Engineer) as they surface during monitor design, evaluation, and iteration\n\nStay current with research on AI safety, agent failures, and detection methodologies\n\nStay current with research into coding security and safety vulnerabilities\n\nFine-tuning & Monitor Development\nFine-tune open-source models to create efficient monitors for high-volume production environments\n\nDesign and build agentic monitoring systems that autonomously investigate logs to identify both known and novel failure modes\n\nIncorporate adversarial findings from red-teaming campaigns into monitor design and evaluation, closing the loop between attack and defense\n\nJOB REQUIREMENTS\nMust-haves\n2+ years of experience conducting empirical research with large language models or AI systems\n\nStrong experience with AI coding agents. For example, having extensively used and compared frontier coding agents, or having designed / developed coding agents\n\nExperience with LLM-as-a-judge setups or AI monitoring more broadly\n\nExperience designing and running experiments, analyzing results, and iterating based on empirical findings e.g. prompting, scaffolding, agent design, fine-tuning, or RL\n\nStrong Python programming skills\n\nDemonstrated ability to work independently on open-ended research problems\n\nGood-to-haves\nFamiliarity with AI safety concepts, particularly agent-related risks\n\nFamiliarity with computer security, e.g. security testing and secure system design\n\nExperience fine-tuning language models or working with smaller open-source models\n\nPrevious work building developer tools or monitoring systems\n\nPublications or contributions to AI safety or ML research\n\nExperience with production log systems or production log analysis\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.\nREPRESENTATIVE PROJECTS\nHierarchical monitoring for coding agent security: Design a multi-layer monitoring system for detecting security vulnerabilities introduced by coding agents. Start by cataloging common security failure modes (e.g., hardcoded credentials, SQL injection vulnerabilities, insecure API calls). Build specialized monitors for each category, then create a hierarchical system where fast, efficient first-pass monitors flag potentially problematic code for deeper investigation by more sophisticated monitors.\n\nDesign a backtesting strategy for Watcher: Validate the system on synthetic test cases and real agent outputs, iterating to optimize the tradeoff between detection rates and false positives while maintaining low latency for most monitoring decisions.\n\nFine-tune an open-source model to be a great monitor: Take an open-source model and fine-tune it on our large dataset of coding agent failures with high-quality ground truth labels. Test different fine-tuning techniques and measure generalization to our held-out data. Compare against prompted baselines on accuracy, cost and latency. The goal is to fine-tune models to lift the pareto frontier of monitors.\n\nBENEFITS\nThis role offers market competitive salary, equity, and competitive benefits.\n\nSalary: San Francisco: $204,000 - $385,000; London: £136,000 - £258,000. We will be looking to meaningfully raise salaries soon.\n\nFlexible work hours and schedule\n\nUnlimited vacation\n\nUnlimited sick leave\n\nUp to 6 months of paid parental leave\n\nComprehensive health, dental and vision insurance\n\nRetirement savings with competitive employer matching (e.g. 401(k) for US employees)\n\nLunch, dinner, and snacks are provided for all employees on workdays\n\nPaid work trips, including staff retreats, business trips, and relevant conferences\n\nA yearly $1,000 (USD) professional development budget\n\nRelocation support and visa fees (if applicable)\n\nLOGISTICS\nTime Allocation: Full-time\n\nLocation: This is an in-person role working out of our London or San Francisco office. We offer flexible working hours and wfh arrangements.\n\nVisa 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":5860,"description_truncated":false,"requirements":{"experience_years_min":2,"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":"2026-10-27T06:21:15+00:00","sources":["UK Home Office: register of licensed sponsors (workers)"],"filings_for_role_12m":0}],"liveness":{"score":16,"band":"cold","label":"Long shot","p_open":1,"p_active":0.457,"p_room":0.36,"age_days":55,"expected_fill_days":28,"reasons":["conf:1","win:tail","crowd:junior"],"computed_at":"2026-10-27T05:46:45Z"},"pay":{"stated_usd_annual":385000,"is_top_pay":true},"html_url":"https://alion.io/job/apollo-research-research-scientist-control","json_url":"https://alion.io/job/apollo-research-research-scientist-control.json","meta":{"generated_at":"2026-10-27T19:59:32Z","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":10874,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-28T00:00:00Z"}},"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-research-scientist-control"},{"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-research-scientist-control"},{"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-research-scientist-control"},{"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-research-scientist-control\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fapollo-research-research-scientist-control"}]}