{"id":3054424,"url":"https://alion.io/job/true-talent-solutions-partners-software-engineer-rl-environments","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":"RLHF","optional":false},{"name":"Synthetic Data","optional":false}],"status":"live","first_seen_at":"2026-10-22T02:23:41Z","employer_posted_date":"2026-10-22","last_verified_at":"2026-10-26T01:13:09Z","board_verified":true,"closed_at":null,"days_open":4,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":4},"description":"About the Role\nDesign datasets, evaluation rubrics, and reward signals that help improve frontier AI models. You will work with research teams to turn training goals into practical experiments and data specifications, with results feeding into model training runs.\nWhat You'll Do\nDesign data slices across finance, software, 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 downstream impact.\n\nCreate and manage real-world and synthetic data pipelines.\n\nPartner with research teams to translate training objectives into data and evaluation specifications.\n\nWhat We're Looking For\nOne to four years of hands-on experience designing machine learning data collection strategies and evaluation rubrics.\n\nStrong familiarity with LLM training and evaluation methods, including experience creating data slices to surface model failure modes.\n\nAbility to run lightweight experiments, work through ambiguous results, and extract actionable insights.\n\nComfort working across domains such as finance, software engineering, and policy.\n\nA practical, builder-oriented approach and a strong interest in how data structure and quality shape model behavior.\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":1544,"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":"2026-10-22T03:11:40Z"}],"visa":[],"liveness":{"score":35,"band":"fade","label":"Fading","p_open":1,"p_active":0.469,"p_room":0.75,"age_days":3,"expected_fill_days":4,"reasons":["conf:3","agency","velocity","win:late","comp:junior,brand"],"computed_at":"2026-10-25T05:49:26Z"},"pay":{"stated_usd_annual":290000,"is_top_pay":true},"html_url":"https://alion.io/job/true-talent-solutions-partners-software-engineer-rl-environments","json_url":"https://alion.io/job/true-talent-solutions-partners-software-engineer-rl-environments.json","meta":{"generated_at":"2026-10-26T03:24:07Z","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":4530,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-27T00:00:00Z"}},"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-software-engineer-rl-environments"},{"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-software-engineer-rl-environments"},{"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-software-engineer-rl-environments"},{"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\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Ftrue-talent-solutions-partners-software-engineer-rl-environments"}]}