{"id":1942465,"url":"https://alion.io/job/clera-full-stack-software-engineer-reinforcement-learning-mid-level","title":"Full-Stack Software Engineer, Reinforcement Learning (Mid-Level)","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":"2026-10-09T06:01:00Z"}},"role":"Backend","role_family":"Backend","seniority":"middle","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":130000,"max":225000,"currency":"USD","period":"year","gross":null,"usd_annual":225000},"salary_estimate":null,"experience_years_min":3,"visa_sponsorship":true,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AWS","optional":false},{"name":"CI/CD","optional":false},{"name":"Docker","optional":false},{"name":"Grafana","optional":false},{"name":"Kubernetes","optional":false},{"name":"Machine Learning","optional":false},{"name":"Next.js","optional":false},{"name":"Python","optional":false},{"name":"React.js","optional":false},{"name":"Reinforcement Learning","optional":false},{"name":"Terraform","optional":false},{"name":"TypeScript","optional":false},{"name":"JavaScript","optional":true}],"status":"live","first_seen_at":"2026-10-06T03:45:26Z","employer_posted_date":"2026-10-06","last_verified_at":"2026-10-10T00:21:32Z","board_verified":true,"closed_at":null,"days_open":3,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":3},"description":"About the Role\nBuild product interfaces, backend services, and internal tools for an AI infrastructure platform focused on reinforcement learning data and evaluation. You will work closely with research, operations, and external partners to turn complex needs into useful, reliable products.\nWhat You'll Do\nDevelop interfaces for browsing environments, inspecting model trajectories, reviewing task quality, and understanding model behavior.\n\nBuild workflows that help external partners create, submit, test, and improve reinforcement learning environments and training data.\n\nCreate dashboards and observability tools for environment quality, evaluation results, data collection progress, and pipeline health.\n\nDesign backend services and APIs that connect task authoring, data collection, evaluation, quality review, and training systems.\n\nCollaborate with research, operations, and go-to-market teams to ship and improve products in a fast-moving environment.\n\nWhat We're Looking For\nAt least 3 years of experience building and shipping production full-stack software.\n\nProficiency in Python and a modern web stack such as React, TypeScript, or Next.js.\n\nHands-on experience with AI, machine learning, or reinforcement learning, plus end-to-end ownership of user-facing or internal products.\n\nExperience building data inspection, review, quality assessment, dashboard, or observability tools.\n\nExperience with backend services, APIs, databases, cloud infrastructure, Docker, CI/CD, and production debugging.\n\nClear communication skills and the ability to work across technical and non-technical teams.\n\nExperience with AWS, Kubernetes, Terraform, Grafana, developer tools, partner workflows, or data collection and evaluation platforms is a plus.\n\nCompensation & Benefits\nSalary range is $130,000 to $225,000 USD annually. Benefits include health coverage, paid time off, and retirement benefits. Visa sponsorship is available for qualified full-time candidates.\nLocation\nOn-site in San Francisco, California, United States.","description_format":"text","description_chars":2027,"description_truncated":false,"requirements":{"experience_years_min":3,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[{"name":"United States","iso":"US","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":[],"lifecycle":[{"event":"open","at":"2026-10-06T04:10:51Z"}],"visa":[],"liveness":{"score":29,"band":"fade","label":"Fading","p_open":1,"p_active":0.317,"p_room":0.9,"age_days":3,"expected_fill_days":6,"reasons":["conf:0","agency","stale_co","velocity","win:mid","comp:brand"],"computed_at":"2026-10-09T06:01:00Z"},"pay":{"stated_usd_annual":225000,"is_top_pay":true},"html_url":"https://alion.io/job/clera-full-stack-software-engineer-reinforcement-learning-mid-level","json_url":"https://alion.io/job/clera-full-stack-software-engineer-reinforcement-learning-mid-level.json","meta":{"generated_at":"2026-10-10T01:09:16Z","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","counted_by":"address","units_charged":1,"used_today":1983,"day_limit":5000,"remaining_today":3017,"minute_limit":60,"resets_at":"2026-10-11T00:00:00Z"}},"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-full-stack-software-engineer-reinforcement-learning-mid-level"},{"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-full-stack-software-engineer-reinforcement-learning-mid-level"},{"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-full-stack-software-engineer-reinforcement-learning-mid-level"},{"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-full-stack-software-engineer-reinforcement-learning-mid-level\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fclera-full-stack-software-engineer-reinforcement-learning-mid-level"}]}