{"id":1536601,"url":"https://alion.io/job/microsoft-senior-applied-scientistresearcheragentic-ai-ai-native","title":"Senior Applied Scientist(Agentic RL & LLM Post-Training)","company":{"id":18,"name":"Microsoft","domain":"microsoft.com","url":"https://alion.io/company/microsoft","size_band":"5000+","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Eightfold","truth_index":{"grade":"B","score":83,"open_postings":363,"ghost_share":0,"stale_share":0.689,"repost_share":0.003,"time_to_fill_p50_days":29,"computed_at":"2026-10-30T05:48:23Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":"senior","employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Suzhou, China","Beijing, China"],"countries":["CN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":40000,"max_usd":103000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":18},"experience_years_min":4,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"GRPO","optional":false},{"name":"LLM","optional":false},{"name":"Machine Learning","optional":false},{"name":"Mixture of Experts","optional":false},{"name":"Post-training","optional":false},{"name":"PPO","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"Quantization","optional":false},{"name":"Reinforcement Learning","optional":false},{"name":"RLAIF","optional":false},{"name":"RLHF","optional":false},{"name":"SFT","optional":false},{"name":"Synthetic Data","optional":false},{"name":"DeepSpeed","optional":true},{"name":"Function Calling","optional":true},{"name":"Megatron-LM","optional":true},{"name":"NVIDIA NeMo","optional":true},{"name":"Reward Modeling","optional":true},{"name":"SGLang","optional":true},{"name":"vLLM","optional":true}],"status":"live","first_seen_at":"2026-09-09T17:46:10Z","employer_posted_date":"2026-10-11","last_verified_at":"2026-10-30T19:15:32Z","board_verified":true,"closed_at":null,"days_open":51,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":51},"description":"OverviewSTCA SAI (Strategic AI Incubation) is an applied science team at Microsoft that incubates strategic AI capabilities. We work on post-training for Agentic scenarios. Starting from strong foundation models, we turn them into high-quality, efficient models that power agentic experiences for users. Our scope covers the full post-training lifecycle: RL and Gym infrastructure, synthetic data generation, and evaluation.\nWe are looking for a Senior Applied Scientist who is passionate about reinforcement learning for LLM agents. You will build the systems, environments, and training recipes that teach models to plan, use tools, and complete complex, multi-step real-world tasks reliably.\nResponsibilities\nAgentic Reinforcement Learning (core focus)\nDesign and run RL post-training for LLM agents on long-horizon, multi-turn, tool-using tasks, such as productivity and document workflows, information seeking, and other complex tasks.\nBuild and scale agentic RL environments, including sandboxed tool execution, task simulators, and trajectory collection that closely reflect real agent behavior.\nDesign reward functions, verifiers, and LLM-as-judge methods for outcome and process supervision that are robust to reward hacking and track real task success.\nAdvance RL algorithms for LLMs (e.g., PPO, GRPO, SAO and variants), including credit assignment over multi-turn trajectories, off-policy correction, and training stability at scale.\nExplore self-improving agents (e.g., RSI), where models help generate the feedback, data, and tasks that improve them.\nLarge-Scale RL Infrastructure\nBuild and extend distributed RL training systems for large models, including Mixture-of-Experts architectures.\nSolve challenging systems problems such as:consistency between rollout and training\nefficient weight synchronization\nlong-context training\nlow-precision and quantization-aware training\nmulti-node scaling on large GPU clusters\n\nData & Evaluation\nBuild high-quality agentic training data through trajectory synthesis, rejection sampling, and gap-driven data curation.\nBuild rigorous evaluation pipelines and fast iteration loops that connect model improvements to user-facing quality.\nQualifications\nRequired Qualifications\nMaster's or PhD in Computer Science, Machine Learning, or a related field, plus 4+ years of hands-on experience with large language models or deep learning (or equivalent experience).\nHands-on experience with reinforcement learning for LLMs (e.g., RLHF, RLAIF, RL with verifiable rewards) at meaningful scale.\nStrong engineering skills in Python (pytorch), and experience with distributed training on multi-node GPU clusters.\nSolid understanding of the LLM post-training pipeline, from data and SFT through RL, evaluation, and deployment.\nPreferred Qualifications\nExperience building agentic RL systems, such as multi-turn tool-use environments, sandboxed execution, and trajectory-level reward design.\nFamiliarity with open-source RL and training frameworks (e.g., verl, NeMo, Megatron-LM, DeepSpeed), including adapting them to new model architectures.\nExperience with inference engines (e.g., vLLM, SGLang), low-precision training, or long-context training techniques.\nExperience with reward modeling, verifiers, or LLM-as-judge methods.\nPublications at top venues (e.g., NeurIPS, ICML, ACL), significant open-source contributions, or patents in LLM, agent, or RL areas.\nComfortable working in a fast-moving incubation environment. You take ownership from idea to production, and you communicate clearly in English with global teams.\nThis position will be open for a minimum of 5 days, with applications accepted on an ongoing basis until the position is filled.\nMicrosoft is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to age, ancestry, citizenship, color, family or medical care leave, gender identity or expression, genetic information, immigration status, marital status, medical condition, national origin, physical or mental disability, political affiliation, protected veteran or military status, race, ethnicity, religion, sex (including pregnancy), sexual orientation, or any other characteristic protected by applicable local laws, regulations and ordinances. If you need assistance with religious accommodations and/or a reasonable accommodation due to a disability during the application process, read more about requesting accommodations.","description_format":"text","description_chars":4450,"description_truncated":false,"requirements":{"experience_years_min":4,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"master","optional":false},"security_clearance":false,"languages":[{"language":"English","level":"All levels","optional":true}]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Console Games","Cloud Platforms (IaaS & PaaS)","Gaming Consoles","Developer Tools"],"lifecycle":[{"event":"open","at":"2026-09-30T18:59:31Z"}],"visa":[],"liveness":{"score":19,"band":"cold","label":"Long shot","p_open":1,"p_active":0.537,"p_room":0.36,"age_days":50,"expected_fill_days":29,"reasons":["conf:4","stale_co","velocity","win:tail","crowd:brand"],"computed_at":"2026-10-30T05:48:23Z"},"pay":null,"html_url":"https://alion.io/job/microsoft-senior-applied-scientistresearcheragentic-ai-ai-native","json_url":"https://alion.io/job/microsoft-senior-applied-scientistresearcheragentic-ai-ai-native.json","meta":{"generated_at":"2026-10-30T22:35:03Z","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":13475,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-31T00:00:00Z"}},"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":18},"rest":"https://alion.io/mcp/rest/get_company?id=18"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fmicrosoft-senior-applied-scientistresearcheragentic-ai-ai-native"},{"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%2Fmicrosoft-senior-applied-scientistresearcheragentic-ai-ai-native"},{"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%2Fmicrosoft-senior-applied-scientistresearcheragentic-ai-ai-native"},{"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/microsoft-senior-applied-scientistresearcheragentic-ai-ai-native\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fmicrosoft-senior-applied-scientistresearcheragentic-ai-ai-native"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":1536601}},{"tool":"search_jobs","arguments":{"company":"microsoft.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":1536601},"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"}}