{"id":2027604,"url":"https://alion.io/job/sigmanova-research-scientist-reinforcement-learning-foundation-models","title":"Research Scientist — Reinforcement Learning (Foundation Models)","company":{"id":3908785,"name":"Sigma Nova","domain":"sigmanova.ai","url":"https://alion.io/company/sigmanova","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Welcome to the Jungle","truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":null,"employment_type":"full_time","work_mode":"hybrid","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Paris, France"],"countries":["FR"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":56000,"max_usd":121000,"period":"year","method":"role_country_seniority_unknown","sample_n":121},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Human-in-the-Loop","optional":false},{"name":"Machine Learning","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"Reinforcement Learning","optional":false},{"name":"Time Series","optional":true}],"status":"live","first_seen_at":"2026-09-22T15:22:37Z","employer_posted_date":"2026-10-07","last_verified_at":"2026-11-02T17:29:28Z","board_verified":true,"closed_at":null,"days_open":41,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":41},"description":"Join our team as a Research Scientist specializing in Reinforcement Learning. In this role, you will focus on integrating RL into the adaptation and improvement of foundation models for industrial use. You will work on human-in-the-loop reinforcement learning, develop RL methods for industrial foundation models, and transition research to deployment. Candidates should have a PhD or equivalent experience in reinforcement learning/machine learning, strong programming skills, and a passion for real-world applications of RL.\nMissions\nResearch and develop reinforcement learning methods that integrate with foundation models used in production.\nDesign feedback interfaces and signals that are practical in real operational settings, turning expert validation into a reliable learning signal.\nBuild evaluation protocols aligned with real constraints, and work closely with scientists and engineers to ship demonstrators that connect benchmarks to field outcomes.\nProfil recherché\n**What we’re looking for*** PhD (preferred) or equivalent research experience in **Reinforcement Learning / Machine Learning**.\n* Strong foundations in RL (e.g., policy optimization, off-policy learning, offline RL, exploration, credit assignment).\n* Ability to design rigorous experiments, debug failure modes, and iterate fast with scientific discipline.\n* Strong programming skills (Python; deep learning stack such as PyTorch).\n**Nice to have**\n* Experience with real-world RL constraints (noisy/limited feedback, safety requirements, deployment considerations).\n* Comfort with complex data modalities (time series, scientific/industrial signals, multimodal setups).\n* Publications or open research artifacts in RL / sequential decision-making.\n**Why join**\n* Work on RL problems that matter in the real world: **expert feedback loops, uncertainty reduction, and mission-critical constraints**.\n* A research culture that values clarity, rigor, and humility and that connects fundamental ideas to deployable systems.\n* High ownership in a small team: you’ll shape direction, not just execute tasks.","description_format":"text","description_chars":2081,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"phd","optional":true},"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[{"name":"France","iso":"FR","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":[],"lifecycle":[{"event":"open","at":"2026-10-07T13:31:27Z"}],"visa":[],"liveness":{"score":13,"band":"cold","label":"Long shot","p_open":1,"p_active":0.377,"p_room":0.35,"age_days":40,"expected_fill_days":17,"reasons":["conf:1","win:tail"],"computed_at":"2026-11-02T06:13:15Z"},"pay":null,"html_url":"https://alion.io/job/sigmanova-research-scientist-reinforcement-learning-foundation-models","json_url":"https://alion.io/job/sigmanova-research-scientist-reinforcement-learning-foundation-models.json","meta":{"generated_at":"2026-11-02T19:22:12Z","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":27142,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-03T00:00:00Z"}},"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":3908785},"rest":"https://alion.io/mcp/rest/get_company?id=3908785"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fsigmanova-research-scientist-reinforcement-learning-foundation-models"},{"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%2Fsigmanova-research-scientist-reinforcement-learning-foundation-models"},{"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%2Fsigmanova-research-scientist-reinforcement-learning-foundation-models"},{"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/sigmanova-research-scientist-reinforcement-learning-foundation-models\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fsigmanova-research-scientist-reinforcement-learning-foundation-models"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":2027604}},{"tool":"search_jobs","arguments":{"company":"sigmanova.ai","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":2027604},"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"}}