{"id":667292,"url":"https://alion.io/job/vmax-research-fellowship-mechanistic-interpretability","title":"Research Fellowship - Mechanistic Interpretability","company":{"id":689574,"name":"VMAX","domain":"vmax.com","url":"https://alion.io/company/vmax-4","size_band":"1-10","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Greenhouse","truth_index":{"grade":"B","score":75,"open_postings":7,"ghost_share":0,"stale_share":1,"repost_share":0,"time_to_fill_p50_days":null,"computed_at":"2026-10-15T05:46:00Z"}},"role":"Science & Research","role_family":"Science & Research","seniority":null,"employment_type":null,"work_mode":"hybrid","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["San Francisco, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":122000,"max_usd":332000,"period":"year","method":"role_country_seniority_unknown","sample_n":3371},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Interpretability","optional":false},{"name":"JAX","optional":false},{"name":"LLM Evaluation","optional":false},{"name":"Machine Learning","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"Reinforcement Learning","optional":false},{"name":"Reward Modeling","optional":false},{"name":"LLM","optional":true},{"name":"Post-training","optional":true}],"status":"live","first_seen_at":"2026-05-20T16:25:29Z","employer_posted_date":"2026-05-20","last_verified_at":"2026-10-16T00:19:02Z","board_verified":true,"closed_at":null,"days_open":148,"trust":{"level":"stale","repost_count":0,"flags":["stale"],"days_open":147},"description":"About Vmax\nVmax is an applied research lab developing AI capable of open-ended learning. We are building systems to exceed humans in all capacities by optimizing beyond the local maxima of learning from human expertise.\nAbout the role\nLLMs are fantastically powerful and there is a rapidly growing corpus of work devoted to understanding their internal representations and computations. We use the tools of mechanistic interpretability to enhance reinforcement learning by generating intrinsic rewards as a supplement or alternative to downstream human-generated verifiers. \nThis 3 to 6 month fellowship is for PhD students or equivalent early-career researchers who want to work at the intersection of mechanistic interpretability and reinforcement learning. You will own a focused research project, work closely with Vmax technical staff, and contribute to research publications.\nResponsibilities\nDevelop mechanistic interpretability methods for understanding internal representations, features, circuits, and computations in language models and agents.\nInvestigate how model internals can be used to generate intrinsic rewards, auxiliary objectives, diagnostics, or training signals for reinforcement learning.\nDesign and run experiments that test whether interpretability-derived signals improve learning, exploration, generalization, robustness, or sample efficiency.\nCompare internally derived rewards against baselines such as human-generated verifiers, reward models, task-level outcome rewards, and standard intrinsic motivation methods.\nUse techniques such as probing, activation analysis, sparse autoencoders, causal interventions, feature attribution, or representation analysis to study model behavior.\nAnalyze failure modes, including reward hacking, spurious features, non-causal correlations, objective misspecification, and overfitting to narrow evaluation distributions.\nBuild research code, evaluation harnesses, and experimental infrastructure that make results reproducible and useful to the broader team.\nCommunicate research progress clearly through written updates, internal presentations, and final project outputs.\nRole Requirements\nCurrently enrolled in a PhD program in machine learning, computer science, artificial intelligence, computational neuroscience, mathematics, or a related technical field. Exceptional candidates with equivalent research experience may also be considered.\nTrack record of research excellence or strong research promise, demonstrated through publications, preprints, open-source work, technical projects, competitions, or publicly available artifacts.\nWorking understanding of reinforcement learning.\nFamiliarity with mechanistic interpretability, representation analysis, or empirical methods for understanding neural networks.\nStrong programming ability in Python and experience with at least one major ML framework such as PyTorch or JAX.\nClear written and verbal communication of technical ideas.\nNice to have\nExperience with LLM post-training methods \nFamiliarity with intrinsic motivation, unsupervised RL, auxiliary objectives, representation learning for RL, or curiosity-driven learning.\nExperience with scalable ML experimentation, distributed training, experiment tracking, or reproducible research infrastructure.\nInterest in turning mechanistic understanding into practical training methods, rather than only analyzing models after training.\nRole specific location policy\nThis role is based in our San Francisco office; for exceptional candidates we are willing to consider a hybrid arrangement","description_format":"text","description_chars":3563,"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":[],"hiring_locations":[{"name":"United States","iso":"US","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Advertising"],"lifecycle":[{"event":"open","at":"2026-09-10T22:05:15Z"}],"visa":[],"liveness":{"score":3,"band":"cold","label":"Long shot","p_open":1,"p_active":0.113,"p_room":0.28,"age_days":147,"expected_fill_days":26,"reasons":["conf:0","win:tail","crowd:"],"computed_at":"2026-10-15T05:46:00Z"},"pay":null,"html_url":"https://alion.io/job/vmax-research-fellowship-mechanistic-interpretability","json_url":"https://alion.io/job/vmax-research-fellowship-mechanistic-interpretability.json","meta":{"generated_at":"2026-10-16T01:54:16Z","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":3036,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-17T00:00:00Z"}},"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":689574},"rest":"https://alion.io/mcp/rest/get_company?id=689574"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fvmax-research-fellowship-mechanistic-interpretability"},{"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%2Fvmax-research-fellowship-mechanistic-interpretability"},{"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%2Fvmax-research-fellowship-mechanistic-interpretability"},{"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/vmax-research-fellowship-mechanistic-interpretability\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fvmax-research-fellowship-mechanistic-interpretability"}]}