{"id":3699990,"url":"https://alion.io/job/true-talent-solutions-partners-founding-reinforcement-learning-engineer-2","title":"Founding Reinforcement Learning Engineer","company":{"id":4415660,"name":"True Talent Solutions Partners","domain":"truetalentsolutionspartners.com","url":"https://alion.io/company/true-talent-solutions-partners","size_band":null,"is_staffing_agency":true,"employer_type":"agency","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":"middle","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"explicit","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":3,"visa_sponsorship":true,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"AWS","optional":false},{"name":"Claude Code","optional":false},{"name":"Cursor","optional":false},{"name":"JAX","optional":false},{"name":"LLM","optional":false},{"name":"Post-training","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"Reinforcement Learning","optional":false},{"name":"Reward Modeling","optional":false},{"name":"RLHF","optional":false},{"name":"TypeScript","optional":false}],"status":"live","first_seen_at":"2026-11-03T17:45:45Z","employer_posted_date":"2026-11-03","last_verified_at":"2026-11-05T00:28:07Z","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 company as its first engineering hire, building coding reinforcement learning environments and AI agents for enterprise use. You will work directly with the founders, shape technical direction, and help grow the engineering team.\nWhat You'll Do\nBuild high-quality reinforcement learning environments and tasks using real-world enterprise data.\n\nBuild and deploy AI agents for enterprise customers.\n\nPartner with company leadership on technical direction and the engineering roadmap.\n\nLead engineering as the team grows, shipping quickly while maintaining a high bar for quality.\n\nWhat We're Looking For\nAt least 3 years of experience in reinforcement learning or AI agent development, or recent-graduate experience that includes 6 to 12 months building reinforcement learning environments or data.\n\nExperience building coding reinforcement learning environments and shipping AI agents into production.\n\nStrong reinforcement learning fundamentals, with experience training models using policy gradients, reward modeling, RLHF, or related methods.\n\nProfessional experience with Python and PyTorch or JAX, plus full-stack experience with TypeScript and AWS.\n\nDaily use of AI-native development tools such as Claude Code, Cursor, or comparable tools.\n\nExperience shipping products at startup pace. Distributed training, GPU infrastructure, mobile development, simulation frameworks, and reinforcement learning training libraries are useful additional experience.\n\nA degree in computer science, mathematics, physics, or a related field is preferred. Experience with LLM post-training, agent training, open-source or research contributions, or early-stage AI teams is also valued.\n\nMust be authorized to work in the United States without visa sponsorship and willing to relocate to San Francisco for an in-person 5.5-day work week.\n\nCompensation & Benefits\nBase salary: $125,000 to $200,000 annually. OTE (on-target earnings, base plus variable): $225,000 to $400,000. Visa sponsorship is not available.\nLocation\nOn-site in San Francisco, California. This role requires relocation to San Francisco and an in-person 5.5-day work week.","description_format":"text","description_chars":2165,"description_truncated":false,"requirements":{"experience_years_min":3,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"bachelor","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":"2026-11-03T19:12:25Z"}],"visa":[],"liveness":{"score":54,"band":"ok","label":"Likely open","p_open":1,"p_active":0.542,"p_room":1,"age_days":0,"expected_fill_days":4,"reasons":["conf:0","agency","velocity","win:early","comp:brand"],"computed_at":"2026-11-04T06:34:25Z"},"pay":{"stated_usd_annual":200000,"is_top_pay":true},"html_url":"https://alion.io/job/true-talent-solutions-partners-founding-reinforcement-learning-engineer-2","json_url":"https://alion.io/job/true-talent-solutions-partners-founding-reinforcement-learning-engineer-2.json","meta":{"generated_at":"2026-11-05T01:13:23Z","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":1436,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-06T00:00:00Z"}},"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":4415660},"rest":"https://alion.io/mcp/rest/get_company?id=4415660"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Ftrue-talent-solutions-partners-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%2Ftrue-talent-solutions-partners-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%2Ftrue-talent-solutions-partners-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/true-talent-solutions-partners-founding-reinforcement-learning-engineer-2\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Ftrue-talent-solutions-partners-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":3699990}},{"tool":"search_jobs","arguments":{"company":"truetalentsolutionspartners.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":3699990},"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"}}