{"id":3362265,"url":"https://alion.io/job/clera-founding-reinforcement-learning-engineer-2","title":"Founding Reinforcement Learning Engineer","company":{"id":2706,"name":"Clera","domain":"getclera.com","url":"https://alion.io/company/clera","size_band":"11-50","is_staffing_agency":true,"employer_type":"agency","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":{"grade":"B","score":80,"open_postings":30,"ghost_share":0,"stale_share":1,"repost_share":0,"time_to_fill_p50_days":6,"computed_at":"2026-10-28T05:59:10Z"}},"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":["San Francisco, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":125000,"max":200000,"currency":"USD","period":"year","gross":null,"usd_annual":200000},"salary_estimate":null,"experience_years_min":2,"visa_sponsorship":true,"relocation_package":false,"has_equity":false,"technologies":[{"name":"DPO","optional":false},{"name":"GRPO","optional":false},{"name":"JAX","optional":false},{"name":"Machine Learning","optional":false},{"name":"PPO","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"Reinforcement Learning","optional":false},{"name":"Reward Modeling","optional":false},{"name":"RLAIF","optional":false},{"name":"RLHF","optional":false},{"name":"LLM","optional":true},{"name":"Post-training","optional":true}],"status":"live","first_seen_at":"2026-10-27T18:21:10Z","employer_posted_date":"2026-10-27","last_verified_at":"2026-10-28T16:20:06Z","board_verified":true,"closed_at":null,"days_open":1,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":1},"description":"About the Role\nJoin an early-stage AI team building reinforcement learning systems from the ground up. You will own the end-to-end process, from environment design and model training to evaluation, helping shape the technical direction and engineering culture.\nWhat You'll Do\nDesign and build reinforcement learning environments, reward functions, and training pipelines.\n\nTrain and fine-tune models using methods such as PPO, GRPO, DPO, RLHF, and RLAIF.\n\nDevelop evaluation frameworks to measure model and agent performance.\n\nRun experiments, interpret results, and decide what to explore next.\n\nScale training on GPU clusters and keep training pipelines reliable.\n\nTurn research ideas into production systems.\n\nHelp establish engineering practices and hire future team members.\n\nWhat We're Looking For\nAt least 2 years of hands-on experience in reinforcement learning or machine learning engineering.\n\nStrong Python skills and deep experience with PyTorch or JAX.\n\nPractical experience training models with reinforcement learning methods, including policy gradients, reward modeling, or RLHF.\n\nExperience with distributed training, GPU infrastructure, RL environments, reward functions, training pipelines, and model or agent evaluation.\n\nA track record of taking research ideas into production systems.\n\nA degree in computer science, mathematics, physics, or a related field; a master's or PhD is a plus.\n\nLLM post-training or agent training experience is beneficial, as are RL publications or open-source work and experience with simulation frameworks or training libraries.\n\nCompensation & Benefits\nBase salary: $125,000 to $200,000 USD annually. Visa sponsorship is available.\nLocation\nOn-site in San Francisco, California, United States. Candidates must be based in or willing to relocate to San Francisco.","description_format":"text","description_chars":1813,"description_truncated":false,"requirements":{"experience_years_min":2,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"master","optional":false},"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[{"name":"United States","iso":"US","kind":"country"}],"hiring_excludes":[],"relocation_offered":true,"industries":[],"lifecycle":[{"event":"open","at":"2026-10-27T21:46:24Z"}],"visa":[],"liveness":{"score":38,"band":"fade","label":"Fading","p_open":1,"p_active":0.379,"p_room":1,"age_days":0,"expected_fill_days":6,"reasons":["conf:3","agency","stale_co","velocity","win:early","comp:junior,brand"],"computed_at":"2026-10-28T05:59:10Z"},"pay":{"stated_usd_annual":200000,"is_top_pay":false},"html_url":"https://alion.io/job/clera-founding-reinforcement-learning-engineer-2","json_url":"https://alion.io/job/clera-founding-reinforcement-learning-engineer-2.json","meta":{"generated_at":"2026-10-28T18:38:56Z","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":25436,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-29T00:00:00Z"}},"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":2706},"rest":"https://alion.io/mcp/rest/get_company?id=2706"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fclera-founding-reinforcement-learning-engineer-2"},{"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%2Fclera-founding-reinforcement-learning-engineer-2"},{"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%2Fclera-founding-reinforcement-learning-engineer-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/clera-founding-reinforcement-learning-engineer-2\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fclera-founding-reinforcement-learning-engineer-2"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":3362265}},{"tool":"search_jobs","arguments":{"company":"getclera.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":3362265},"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"}}