{"id":4321064,"url":"https://alion.io/job/true-talent-solutions-partners-software-engineer-rl-environments-5","title":"Software Engineer, RL Environments","company":{"id":4415660,"name":"True Talent Solutions Partners","domain":"truetalentsolutionspartners.com","url":"https://alion.io/company/true-talent-solutions-partners","size_band":"11-50","is_staffing_agency":true,"employer_type":"agency","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":null},"role":"Backend","role_family":"Backend","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":260000,"max":290000,"currency":"USD","period":"year","gross":null,"usd_annual":290000},"salary_estimate":null,"experience_years_min":1,"visa_sponsorship":true,"relocation_package":false,"has_equity":false,"technologies":[{"name":"LLM","optional":false},{"name":"Machine Learning","optional":false},{"name":"Post-training","optional":false},{"name":"Python","optional":false},{"name":"Reward Modeling","optional":false},{"name":"RLHF","optional":false},{"name":"Synthetic Data","optional":false}],"status":"live","first_seen_at":"2026-11-14T17:38:20Z","employer_posted_date":"2026-11-14","last_verified_at":"2026-11-14T20:25:10Z","board_verified":true,"closed_at":null,"days_open":0,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":0},"description":"About the Role\nJoin a Series A AI training data company building datasets and evaluation systems for frontier models. You will work with research teams to design experiments, identify model failure modes, and create data and metrics that inform model training.\nWhat You'll Do\nDesign data slices across finance, software development, and enterprise workflows to reveal meaningful model failure modes.\n\nBuild and refine evaluation rubrics and reward signals for RLHF and RLVR pipelines.\n\nModel annotator behavior and run experiments to improve model capabilities.\n\nDevelop quantitative frameworks to measure dataset quality, diversity, and downstream effects on model alignment and capability.\n\nCreate and manage real-world and synthetic data pipelines.\n\nPartner with research teams to translate training objectives into concrete data and evaluation specifications.\n\nWhat We're Looking For\n1 to 4 years of software engineering experience building reliable data pipelines, experimentation infrastructure, or evaluation systems.\n\nStrong Python skills and experience shipping software and infrastructure.\n\nHands-on experience with LLM evaluations, model post-training, reward modeling, RLHF, RLVR, or related ML infrastructure.\n\nStrong experimental judgment, including forming hypotheses, defining metrics, designing controlled experiments, and interpreting noisy results.\n\nExperience creating or evaluating datasets, measuring quality, diversity, coverage, and downstream model performance.\n\nExperience designing data collection strategies and evaluation rubrics for machine learning models.\n\nExperience in AI safety, benchmarking, model evaluation, or research engineering is beneficial.\n\nCompensation & Benefits\nBase salary: $260,000 to $290,000 annually. Visa sponsorship is available.\nLocation\nOn-site in San Francisco, California.","description_format":"text","description_chars":1831,"description_truncated":false,"requirements":{"experience_years_min":1,"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":[],"lifecycle":[{"event":"open","at":"2026-11-14T20:25:10Z"}],"visa":[{"country":"US","licensed_sponsor":false,"adverts_offering_sponsorship_24m":89,"sanctioned_now":false,"evidence":"Offered visa sponsorship in 89 of its adverts here in 24 months","filings_12m":0,"filings_prev_12m":0,"green_card_filings_12m":0,"median_offered_wage_usd":null,"route":null,"cap_exempt":false,"checked_at":"2026-11-14T07:33:33+00:00","sources":["Alion: sponsorship offered in the employer's own job adverts (24 months)"],"filings_for_role_12m":0}],"liveness":{"score":52,"band":"ok","label":"Likely open","p_open":1,"p_active":0.516,"p_room":1,"age_days":0,"expected_fill_days":4,"reasons":["conf:1","agency","win:early","comp:junior,brand"],"computed_at":"2026-11-14T22:09:43Z"},"pay":{"stated_usd_annual":290000,"is_top_pay":true},"html_url":"https://alion.io/job/true-talent-solutions-partners-software-engineer-rl-environments-5","json_url":"https://alion.io/job/true-talent-solutions-partners-software-engineer-rl-environments-5.json","meta":{"generated_at":"2026-11-14T22:09:43Z","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":28867,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-15T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.1,"usd":0.01,"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-software-engineer-rl-environments-5"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"free","price":{"credits":0,"usd":0},"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-software-engineer-rl-environments-5"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.1,"usd":0.01},"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-software-engineer-rl-environments-5"},{"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-software-engineer-rl-environments-5\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Ftrue-talent-solutions-partners-software-engineer-rl-environments-5"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":4321064}},{"tool":"search_jobs","arguments":{"company":"truetalentsolutionspartners.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":4321064},"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"}}