{"id":3907784,"url":"https://alion.io/job/true-talent-solutions-partners-software-engineer-rl-environments-4","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":null,"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":"2026-11-07T02:45:25Z","employer_posted_date":"2026-11-07","last_verified_at":"2026-11-10T01:51:07Z","board_verified":true,"closed_at":null,"days_open":2,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":2},"description":"About the Role\nBuild data and evaluation systems that shape how advanced AI models learn and improve. You will work with research teams to turn training objectives into practical datasets, experiments, and evaluation specifications.\nWhat You'll Do\nDesign data slices across finance, code, 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 approaches to measure dataset quality, diversity, and impact on model alignment and capabilities.\n\nCreate and manage real-world and synthetic data pipelines.\n\nCollaborate with research teams to translate training objectives into concrete data and evaluation specifications.\n\nWhat We're Looking For\nOne to four years of software engineering experience building reliable data pipelines, experimentation infrastructure, or evaluation systems.\n\nStrong Python skills and a track record of shipping software and infrastructure.\n\nHands-on experience with LLM evaluations, model post-training, reward modeling, RLHF or RLVR, or related machine learning infrastructure.\n\nExperience creating or evaluating datasets, including assessing quality, diversity, coverage, and downstream model performance.\n\nStrong experimental judgment, including forming hypotheses, defining metrics, designing controlled experiments, and interpreting noisy results.\n\nExperience designing data collection strategies and evaluation rubrics for machine learning models.\n\nWork in AI safety, benchmarking, model evaluation, or open-source evaluation projects is relevant.\n\nCompensation & Benefits\nBase salary is $260,000 to $290,000 annually. Visa sponsorship is available.\nLocation\nOn-site in San Francisco, California.","description_format":"text","description_chars":1824,"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":"2026-11-07T04:40:43Z"}],"visa":[{"country":"US","licensed_sponsor":false,"adverts_offering_sponsorship_24m":97,"sanctioned_now":false,"evidence":"Offered visa sponsorship in 97 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":"2026-11-09T07:32:21+00:00","sources":["Alion: sponsorship offered in the employer's own job adverts (24 months)"],"filings_for_role_12m":0}],"liveness":{"score":47,"band":"ok","label":"Likely open","p_open":1,"p_active":0.526,"p_room":0.9,"age_days":2,"expected_fill_days":4,"reasons":["conf:0","agency","velocity","win:mid","comp:junior,brand"],"computed_at":"2026-11-09T06:03:00Z"},"pay":{"stated_usd_annual":290000,"is_top_pay":true},"html_url":"https://alion.io/job/true-talent-solutions-partners-software-engineer-rl-environments-4","json_url":"https://alion.io/job/true-talent-solutions-partners-software-engineer-rl-environments-4.json","meta":{"generated_at":"2026-11-10T01:52:28Z","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":4341,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-11T00:00:00Z"}},"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-4"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":2,"usd":0.2},"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-4"},{"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-4"},{"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-4\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Ftrue-talent-solutions-partners-software-engineer-rl-environments-4"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":3907784}},{"tool":"search_jobs","arguments":{"company":"truetalentsolutionspartners.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":3907784},"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"}}