{"id":4103665,"url":"https://alion.io/job/raydar-reinforcement-learning-researcher-2","title":"Reinforcement Learning Researcher","company":{"id":4478753,"name":"Raydar","domain":"raydar.com","url":"https://alion.io/company/raydar-com","size_band":"51-200","is_staffing_agency":true,"employer_type":"agency","is_intermediary":false,"listed_via":null,"ats_vendor":"Workable","truth_index":{"grade":"B","score":75,"open_postings":7,"ghost_share":0,"stale_share":1,"repost_share":0,"time_to_fill_p50_days":22,"computed_at":"2026-11-11T05:49:22Z"}},"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":"structured","locations":["San Francisco, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":200000,"max":350000,"currency":"USD","period":"year","gross":null,"usd_annual":350000},"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Machine Learning","optional":false},{"name":"Multimodal AI","optional":false},{"name":"Reinforcement Learning","optional":false},{"name":"Reinforcement Learning","optional":false},{"name":"JAX","optional":true},{"name":"Sim-to-Real","optional":true}],"status":"live","first_seen_at":"2026-11-11T22:11:00Z","employer_posted_date":"2026-11-11","last_verified_at":"2026-11-11T22:11:00Z","board_verified":true,"closed_at":null,"days_open":0,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":0},"description":"About the company\nOur client is a technology company.\nThe role\nRaydar is recruiting for this role on behalf of our client. Lead a research agenda in offline reinforcement learning, taking ideas from initial question through to shared findings. The position prizes scientific depth and judgment over engineering breadth, and pairs you with a more established colleague while leaving space to chart your own path.\nWhat you'll do\n- Drive offline reinforcement learning research from start to finish, including choosing which questions to pursue and communicating the outcomes.\n- Raise the performance of learned control policies on internal evaluation suites and build on earlier policy work.\n- Train models on large, uneven-quality collections of data where feedback is scarce, applying several value estimation approaches.\n- Investigate model-based methods and learned environment models for continuous control.\n- Examine what keeps reinforcement learning training stable as data, compute and model scale increase.\n- Design rigorous experiments with dependable baselines and watch findings get tested on physical robots.\nRequirements\nWhat we're looking for\n- Background in reinforcement learning research, in a research or applied scientist capacity, connected to generative visual models.\n- A record of papers accepted at leading machine learning or robotics venues.\n- Depth in core and offline reinforcement learning topics, such as value estimation, goal-directed learning, policy design and training stability at scale.\n- Familiarity with model-based methods for continuous control or with multimodal value estimation.\n- An advanced degree (PhD or master's) in machine learning, computer science or an adjacent area, centered on reinforcement learning.\n- Ability to work on-site six days a week.\nBonus points\n- Prior exposure to visual generative models applied to robotics.\n- Time spent doing research at a top-tier AI organization.\n- Contributions to publicly shared reinforcement learning codebases.\n- Experience with large-scale simulation, sim-to-real transfer or robotics, including JAX.\nBenefits\nCompensation and benefits\n- Base salary: USD 200,000 to 350,000 per year\n- Equity\n- Health, dental and vision coverage\nLocation and work model\n- San Francisco, CA, United States\n- On-site, 6 days per week in office\n- Full-time","description_format":"text","description_chars":2332,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":["Equity"],"hiring_locations":[{"name":"United States","iso":"US","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":[],"lifecycle":[{"event":"open","at":"2026-11-11T22:11:00Z"}],"visa":[{"country":"US","licensed_sponsor":false,"adverts_offering_sponsorship_24m":32,"sanctioned_now":false,"evidence":"Offered visa sponsorship in 32 of its adverts here in 24 months","filings_12m":0,"filings_prev_12m":0,"green_card_filings_12m":0,"median_offered_wage_usd":null,"route":null,"cap_exempt":false,"checked_at":"2026-11-11T07:38:50+00:00","sources":["Alion: sponsorship offered in the employer's own job adverts (24 months)"],"filings_for_role_12m":0}],"liveness":{"score":52,"band":"ok","label":"Likely open","p_open":1,"p_active":0.516,"p_room":1,"age_days":0,"expected_fill_days":22,"reasons":["conf:2","agency","win:early","comp:brand"],"computed_at":"2026-11-12T01:00:17Z"},"pay":{"stated_usd_annual":350000,"is_top_pay":true},"html_url":"https://alion.io/job/raydar-reinforcement-learning-researcher-2","json_url":"https://alion.io/job/raydar-reinforcement-learning-researcher-2.json","meta":{"generated_at":"2026-11-12T01:00:17Z","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":2337,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-13T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.1,"usd":0.01,"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":4478753},"rest":"https://alion.io/mcp/rest/get_company?id=4478753"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fraydar-reinforcement-learning-researcher-2"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":2,"usd":0.2},"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%2Fraydar-reinforcement-learning-researcher-2"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.1,"usd":0.01},"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%2Fraydar-reinforcement-learning-researcher-2"},{"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/raydar-reinforcement-learning-researcher-2\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fraydar-reinforcement-learning-researcher-2"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":4103665}},{"tool":"search_jobs","arguments":{"company":"raydar.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":4103665},"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"}}