{"id":1145253,"url":"https://alion.io/job/far-ai-research-scientist-applied-white-box-methods","title":"Research Scientist, Applied White-Box Methods","company":{"id":24025,"name":"FAR.AI","domain":"far.ai","url":"https://alion.io/company/far","size_band":"51-200","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":{"grade":"A","score":89,"open_postings":12,"ghost_share":0,"stale_share":0.25,"repost_share":0,"time_to_fill_p50_days":67,"computed_at":"2026-10-20T05:45:00Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":null,"employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"explicit","locations":["Berkeley, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":150000,"max":250000,"currency":"USD","period":"year","gross":null,"usd_annual":250000},"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":true,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"Anthropic","optional":false},{"name":"Chain-of-Thought","optional":false},{"name":"Interpretability","optional":false},{"name":"OpenAI","optional":false},{"name":"Post-training","optional":false},{"name":"Reinforcement Learning","optional":false},{"name":"Reinforcement Learning","optional":false},{"name":"Machine Learning","optional":true}],"status":"live","first_seen_at":"2026-09-23T13:22:25Z","employer_posted_date":"2026-09-28","last_verified_at":"2026-10-20T07:07:52Z","board_verified":true,"closed_at":null,"days_open":26,"trust":{"level":"ok","repost_count":0,"flags":[],"days_open":26},"description":"About Us\nFAR.AI is a non-profit AI research institute working to ensure advanced AI is safe and beneficial for everyone. Our mission is to facilitate breakthrough AI safety research, advance global understanding of AI risks and solutions, and foster a coordinated global response. \nSince our founding in July 2022, we've grown to 50+ staff, published 40+ academic papers, and convened leading AI safety events. Our work is recognized globally, with publications at premier venues such as NeurIPS, ICML including a Best Paper Honorable Mention in 2026, and ICLR, and features in the Financial Times, Nature News, Wired Magazine and MIT Technology Review. We conduct pre-deployment testing on behalf of frontier developers such as OpenAI, independent evaluations for governments including the EU AI Office, and publish the AI Security Leaderboard based on our red-teaming expertise. We help steer and grow the AI safety field through developing research roadmaps with renowned researchers such as Yoshua Bengio; running FAR.Labs, an AI safety-focused co-working space in Berkeley housing 40+ members; and supporting the community through targeted grants to technical researchers.\nAbout the Applied White-Box Methods team\nThe Applied White-Box Methods team develops, evaluates, and demonstrates methods that leverage model internals to improve the safety of AI systems. We work on diverse AI safety applications of white-box methods, from white-box control to evaluation awareness to shaping training dynamics to improve alignment.\nBlack-box methods, such as chain-of-thought monitoring, work well for now, but we are quickly entering a world where black-box interventions and monitoring are insufficient. Interpretability research is still often early-stage, curiosity-driven work without realistic evaluations on applications that matter. The team bridges the gap between exploration and deployment by stress-testing white-box methods on real-world (e.g. long-context agentic coding) tasks and using this feedback loop to enable the deployment of better white-box methods at frontier scale.\nOur scope includes any method that uses model internals to understand, predict, or intervene on model behavior, not only what is conventionally called interpretability. Methods of current interest include natural language autoencoders and other activation explainers, activation oracles, steering, patching, and other activation-level interventions, influence functions and data attribution, and singular learning theory. We evaluate our methods against real baselines - strong black-box methods and activation probes - to be able to make an honest case that the methods are worth implementing, or conclude that simpler methods work better for now.\nAI Research Automation. AI will soon automate most of the hill-climbing in the research process. We anticipate this by focusing our effort and judgement on defining realistic evaluations with Goodhart-resistant metrics. With the evaluation framework properly built, we can pour vast amounts of AI labor into method development and iteration without overfitting. We believe this is the way to scale white-box research into the age of RSI.\nRealistic, large-scale models. Unrealistic models lead to unconfident conclusions about which methods do and do not work. We leverage FAR's shared compute and infrastructure to work on organisms that come out of pipelines a frontier lab could plausibly have run: for example, reward seekers trained by RL in broken environments, with other contaminated data mixed in to induce other misalignments.\nRealistic, large-scale evaluations. We will primarily study long-context agentic coding as this is where most of the risk currently lies. In addition to the classic AI control sabotage settings, we will also study reward hacking, sandbagging, and research tampering, which are some of the key failure modes that matter during RSI.\nPractical monitors and interventions. Deployment of new methods has real costs for AI developers. Part of our focus on real-world applications is ensuring that methods are simple and efficient enough to deploy at frontier scale.\nAbout the Role\nAs a Research Scientist on the team, you will take ownership of and accelerate the team's research agenda, publish findings broadly, and engage with the AI alignment community. You are encouraged to propose new directions within the team's agenda. You are welcome and encouraged to attend relevant conferences and other community events, and leverage FAR.AI ’s existing comprehensive infrastructure for events convening and government relations as you see fit. Beyond FAR.AI, you can work with national AI safety institutes, frontier model developers, and top academics.\nAbout You\nTwo backgrounds are particularly well suited to this role: researchers with some experience in more fundamental interpretability who want to evaluate and refine those methods in realistic settings, including agentic coding, long contexts, and realistic threat models; and researchers from evaluations, AI control, red-teaming, or reinforcement learning who have begun working with model internals and want to deepen that work. In both cases, prior hands-on experience with white-box methods and a demonstrated interest in their practical application are preferred. (Note that this role is not well suited to researchers whose primary interest is interpretability as a foundational science.)\nIf you are new to AI Safety research, that is also ok! But please be prepared to explain how your previous research experience (e.g. in applied ML) could be leveraged for our work, and how you are engaging with the field of technical AI safety research today.\nWe are hiring across a range of levels of experience. You may already have some of the following, though not necessarily all.\nHands-on experience applying at least one white-box method to a real model (activation explainers, SAEs, steering, attribution, influence functions, probes, or similar), and an informed view of its limitations.\n\nA track record in AI safety: a paper, a fellowship project, or substantive public writing. Alumni of programs such as MATS, Astra, Anthropic Fellows, SPAR, Pivotal, LASR or similar programs are especially encouraged to apply.\n\nExperience with evaluations, AI control, red-teaming, reinforcement learning, or post-training of LLMs. Experience running large training runs is a plus.\n\nThe ability to communicate novel methods and results clearly to technical and non-technical audiences.\n\nA PhD or several years of research experience in computer science, machine learning, physics, statistics, or a related field.\n\nPrevious experience in applied ML for other fields: e.g. biology, chemistry, materials science, robotics, etc.\n\nBenefits*\nHealth Insurance - 94% of Insurance premium paid by Organization commencing within 1 month after your start date\n\nRetirement - 401(k) plan with up to 2% match\n\nPTO - 25 days Paid Time Off per year, accrued weekly and up to 10 days of paid sick leave per year\n\nPaid Leave - Paid Bereavement, Family, Medical and Pregnancy Disability Leave\n\nWFH Stipend & Equipment - Work computer and stipend provided for eligible employees\n\nCatered Meals (Berkeley Office Only) - Catered lunches and dinners on workdays at our office\n\n*(Available only to full-time employees located in the US)\nLogistics\nIf based in the USA, you will be an employee of FAR.AI, a 501(c)(3) research non-profit. Outside the USA, you will be an employee of an EoR organization on behalf of FAR.AI.\n\nLocation: Berkeley, CA. This role is in-person; we strongly prefer candidates who are in the Bay Area or willing to relocate, and we sponsor visas for in-person employees. We will consider remote arrangements for exceptional candidates.\n\nHours: full-time (40 hours/week).\n\nCompensation: $150,000-$250,000/year depending on experience and location, plus work-related travel and equipment expenses. Catered lunch and dinner at our Berkeley office.\n\nApplication process: interviews with members of our technical staff, followed by a paid work trial of up to one week. If you are not available for a work trial we may be able to find alternative ways of assessing fit.\n\nIf you have any questions about the role, feel free to contact us at . Otherwise, if you don't have questions, the best way to ensure a proper review of your skills and qualifications is by applying directly via the application form. Please don't email us to share your resume (it won't have any impact on our decision). Thank you!","description_format":"text","description_chars":8527,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"phd","optional":false},"security_clearance":false,"languages":[]},"benefits":["Health insurance","Retirement plans"],"hiring_locations":[{"name":"United States","iso":"US","kind":"country"}],"hiring_excludes":[],"relocation_offered":true,"industries":["AI Safety & Alignment","AI Research Labs","Nonprofits & Foundations"],"lifecycle":[{"event":"open","at":"2026-09-23T14:43:54Z"}],"visa":[{"country":"US","licensed_sponsor":true,"evidence":"H-1B filings in 12 months: 5","filings_12m":5,"filings_prev_12m":3,"green_card_filings_12m":0,"median_offered_wage_usd":187500,"route":null,"cap_exempt":false,"checked_at":"2026-10-15T11:24:14+00:00","sources":["US Department of Labor: LCA disclosure data (H-1B, H-1B1, E-3)"],"filings_for_role_12m":4}],"liveness":{"score":74,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.817,"p_room":0.9,"age_days":26,"expected_fill_days":67,"reasons":["conf:2","velocity","win:mid"],"computed_at":"2026-10-20T05:45:00Z"},"pay":{"stated_usd_annual":250000,"is_top_pay":true},"html_url":"https://alion.io/job/far-ai-research-scientist-applied-white-box-methods","json_url":"https://alion.io/job/far-ai-research-scientist-applied-white-box-methods.json","meta":{"generated_at":"2026-10-20T11:52:26Z","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":13153,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-21T00:00:00Z"}},"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":24025},"rest":"https://alion.io/mcp/rest/get_company?id=24025"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Ffar-ai-research-scientist-applied-white-box-methods"},{"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%2Ffar-ai-research-scientist-applied-white-box-methods"},{"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%2Ffar-ai-research-scientist-applied-white-box-methods"},{"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/far-ai-research-scientist-applied-white-box-methods\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Ffar-ai-research-scientist-applied-white-box-methods"}]}