{"id":2052465,"url":"https://alion.io/job/baseten-post-training-applied-researcher","title":"Post-Training Applied Researcher","company":{"id":4399,"name":"Baseten","domain":"baseten.co","url":"https://alion.io/company/baseten","size_band":"1001-5000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":{"grade":"B","score":72,"open_postings":16,"ghost_share":0,"stale_share":0.938,"repost_share":0,"time_to_fill_p50_days":92,"computed_at":"2026-10-14T06:34:16Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":null,"employment_type":"full_time","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":{"min":200000,"max":275000,"currency":"USD","period":"year","gross":null,"usd_annual":275000},"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Agentic Workflows","optional":false},{"name":"Baseten","optional":false},{"name":"Cursor","optional":false},{"name":"DPO","optional":false},{"name":"Fine-tuning","optional":false},{"name":"Function Calling","optional":false},{"name":"GRPO","optional":false},{"name":"Knowledge Distillation","optional":false},{"name":"KV Cache","optional":false},{"name":"LLM","optional":false},{"name":"LLM Evaluation","optional":false},{"name":"Model Distillation","optional":false},{"name":"Post-training","optional":false},{"name":"PPO","optional":false},{"name":"Reinforcement Learning","optional":false},{"name":"SFT","optional":false},{"name":"Synthetic Data","optional":false},{"name":"Tool Use","optional":false},{"name":"Machine Learning","optional":true},{"name":"Reward Modeling","optional":true}],"status":"live","first_seen_at":"2026-10-07T20:22:30Z","employer_posted_date":"2026-10-07","last_verified_at":"2026-10-14T07:46:04Z","board_verified":true,"closed_at":null,"days_open":6,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":6},"description":"ABOUT BASETEN\nBaseten powers mission-critical inference for the world's most dynamic AI companies, like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma, and Writer. By uniting applied AI research, flexible infrastructure, and seamless developer tooling, we enable companies operating at the frontier of AI to bring cutting-edge models into production. We're growing quickly and recently raised our $1.5B Series F, led by Altimeter Capital, Conviction Partners, and Spark Capital. Join us and help build the platform engineers turn to ship AI products.\nTHE ROLE\nThis role sits at the applied end of our post-training research efforts. You will work directly with stakeholders from the world’s fastest-growing AI companies to post-train open-source models that outperform frontier closed models on their specialised tasks. Your day-to-day is finding creative ways to extract signal from complex, domain-specific datasets and building the reward functions, environments, eval harnesses, and training pipelines that turn that signal into better models. The models you train ship to production and reach millions of users.\nWe are looking for people with hands-on LLM fine-tuning and RL experience. Researchers who are excited by the prospect of shipping models into production, who can translate a customer's domain-specific requirements into an effective training curriculum, and who know when to be rigorous and when to iterate fast.\nRECENT RESEARCH\nDense, on-policy or both?\n\nRepeated kv cache for long-running agents\n\nDistillation without the dark - replicating black-box on-policy distillation on Baseten\n\nRESPONSIBILITIES\nDesign and run post-training pipelines: SFT, GRPO, DPO, RLVR, reward function engineering, and synthetic data generation.\n\nBuild task-specific training environments and evals tailored to customer domains like healthcare, code generation, and legal, spanning multi-turn tool use, sandboxed execution, and agentic workflows.\n\nWork directly with customers to translate production data into training signal, designing reward loops from real usage patterns and handling distribution shift.\n\nRun and analyze training experiments end-to-end: diagnose reward hacking, importance sampling drift, and advantage estimation instabilities.\n\nPublish findings at top venues and contribute to Baseten's open-source training libraries.\n\nQUALIFICATIONS\nHands-on experience training LLMs with reinforcement learning - demonstrated understanding of GRPO or PPO beyond recipe-level reproduction, including group advantage computation, clipped objectives, and KL penalty design\n\nStrong intuition for reward engineering: the ability to distinguish between a reward that trains effectively and one that will exploit at scale\n\nExperience building multi-turn agent environments with tool use, not limited to single-turn question-answering setups\n\nComfort working across the full pipeline from dataset construction through training, evaluation, and deployment\n\nExperience with production ML systems. Preference for candidates who have closed a training-inference loop where production data feeds back into model improvement\n\nPREFERRED QUALIFICATIONS\nExperience with RL training frameworks\n\nPublications at NeurIPS, ICML, ICLR, focused on RL for LLMs, reward modeling, or alignment\n\nBENEFITS\nCompetitive compensation, including meaningful equity\n\n(U.S. only) 100% coverage of medical, dental, and vision insurance for employee and dependents\n\nFlexible PTO policy including company wide Winter Break (our offices are closed from Christmas Eve to New Year's Day!)\n\nPaid parental leave\n\nFertility and family-building stipend through Carrot\n\n(U.S. only) Company-facilitated 401(k)\n\nExposure to a variety of ML startups, offering unparalleled learning and networking opportunities.\n\nApply now to embark on a rewarding journey in shaping the future of AI! If you are a motivated individual with a passion for machine learning and a desire to be part of a collaborative and forward-thinking team, we would love to hear from you.\nAt Baseten, we are committed to fostering a diverse and inclusive workplace. We provide equal employment opportunities to all employees and applicants without regard to race, color, religion, gender, sexual orientation, gender identity or expression, national origin, age, genetic information, disability, or veteran status.\nWe are an Equal Opportunity Employer and will consider qualified applicants with criminal histories in a manner consistent with applicable law (by example, the requirements of the San Francisco Fair Chance Ordinance, where applicable).","description_format":"text","description_chars":4580,"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","Parental leave","Vision insurance"],"hiring_locations":[{"name":"United States","iso":"US","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["MLOps","AI Compute & Inference"],"lifecycle":[{"event":"open","at":"2026-10-07T22:19:38Z"}],"visa":[],"liveness":{"score":63,"band":"ok","label":"Likely open","p_open":1,"p_active":0.632,"p_room":1,"age_days":6,"expected_fill_days":92,"reasons":["conf:3","stale_co","velocity","win:early","comp:brand"],"computed_at":"2026-10-14T06:34:16Z"},"pay":{"stated_usd_annual":275000,"is_top_pay":true},"html_url":"https://alion.io/job/baseten-post-training-applied-researcher","json_url":"https://alion.io/job/baseten-post-training-applied-researcher.json","meta":{"generated_at":"2026-10-14T08:08:18Z","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":"search","counted_by":"address","units_charged":0,"used_today":0,"day_limit":null,"remaining_today":null,"minute_limit":null,"resets_at":"2026-10-15T00:00:00Z"}},"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":4399},"rest":"https://alion.io/mcp/rest/get_company?id=4399"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fbaseten-post-training-applied-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%2Fbaseten-post-training-applied-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%2Fbaseten-post-training-applied-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/baseten-post-training-applied-researcher\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fbaseten-post-training-applied-researcher"}]}