{"id":2314607,"url":"https://alion.io/job/pluto-rl-environment-software-engineer-afterquery","title":"RL Environment Software Engineer - AfterQuery","company":{"id":3514,"name":"Pluto","domain":"talentpluto.com","url":"https://alion.io/company/talentpluto","size_band":"51-200","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Workable","truth_index":null},"role":"Backend","role_family":"Backend","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":180000,"max":220000,"currency":"USD","period":"year","gross":null,"usd_annual":220000},"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Docker","optional":false},{"name":"Kubernetes","optional":false},{"name":"Node JS","optional":false},{"name":"Python","optional":false},{"name":"React.js","optional":false},{"name":"Reinforcement Learning","optional":false},{"name":"TypeScript","optional":false},{"name":"JavaScript","optional":true}],"status":"live","first_seen_at":"2026-10-12T03:34:17Z","employer_posted_date":"2026-10-12","last_verified_at":"2026-10-12T03:34:17Z","board_verified":true,"closed_at":null,"days_open":0,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":0},"description":"Location: San Francisco, CA\nWork Model: Onsite\nIndustry: Applied AI / AI research data\nCompensation: $180K-$220K base, ~$400K+ OTE (uncapped profit share)\nAbout the Company\nOur partner is a fast-growing applied AI research lab that builds high-quality reinforcement-learning environments and agents sold to the world's leading AI labs. In under two years they have scaled to a nine-figure revenue run rate and grown their team severalfold in a matter of months, backed by leading venture investors. Quality is their core differentiator, and they are rapidly expanding into new domains.\nThe Opportunity\nAs an RL Environment Software Engineer, you will sit at the intersection of research engineering and traditional software engineering, building the environments that simulate real-world workflows and the agents that automate them. This is forward-looking work, you will help research and predict what high-quality environments the frontier will need next, then build them from the ground up.\nYou will join a brand-new RL team being assembled with exceptional talent, with a clear path to grow alongside it as the function scales into industry pods.\nResponsibilities\nDesign and build high-quality RL environments that simulate real working environments end to end.\nDevelop agents for the tasks within those environments and iterate until they are efficient and production-ready.\nPartner with the research team to scope which environments to build and why, staying ahead of future demand rather than only meeting present needs.\nOwn the backend and infrastructure layers that make environments reliable and scalable.\nHelp set engineering standards for a zero-to-one team as the RL function grows.\nRequirements\nStrong machine-learning engineers who code heavily and build systems from scratch, with strong intuition for reinforcement learning.\nProficiency across a modern stack, Node.js and Python on the backend and React/TypeScript on the frontend, with strong Kubernetes and Docker skills.\nComfort operating in a fast-paced startup environment with high ownership and long hours.\nA track record of meaningful tenure and impact at previous companies.\nReinforcement-learning experience or an RL research background is a strong plus, though not required.\nBachelor's degree in computer science or a related technical field, or equivalent practical experience.","description_format":"text","description_chars":2356,"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":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Conversational AI","Recruiting & Staffing","Career Services","HR & Recruiting AI"],"lifecycle":[{"event":"open","at":"2026-10-12T03:34:17Z"}],"visa":[],"liveness":{"score":86,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.86,"p_room":1,"age_days":0,"expected_fill_days":22,"reasons":["conf:3","win:early"],"computed_at":"2026-10-12T06:55:09Z"},"pay":{"stated_usd_annual":220000,"is_top_pay":true},"html_url":"https://alion.io/job/pluto-rl-environment-software-engineer-afterquery","json_url":"https://alion.io/job/pluto-rl-environment-software-engineer-afterquery.json","meta":{"generated_at":"2026-10-12T08:45:31Z","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":13100,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-13T00:00:00Z"}},"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":3514},"rest":"https://alion.io/mcp/rest/get_company?id=3514"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fpluto-rl-environment-software-engineer-afterquery"},{"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%2Fpluto-rl-environment-software-engineer-afterquery"},{"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%2Fpluto-rl-environment-software-engineer-afterquery"},{"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/pluto-rl-environment-software-engineer-afterquery\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fpluto-rl-environment-software-engineer-afterquery"}]}