{"id":3027685,"url":"https://alion.io/job/true-talent-solutions-partners-machine-learning-infrastructure-engineer-2","title":"Machine Learning Infrastructure Engineer","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":"AI/ML","role_family":"AI/ML","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":200000,"max":400000,"currency":"USD","period":"year","gross":null,"usd_annual":400000},"salary_estimate":null,"experience_years_min":2,"visa_sponsorship":true,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AWS","optional":false},{"name":"Azure","optional":false},{"name":"CUDA","optional":false},{"name":"DeepSpeed","optional":false},{"name":"Docker","optional":false},{"name":"FSDP","optional":false},{"name":"GCP","optional":false},{"name":"JAX","optional":false},{"name":"Kubernetes","optional":false},{"name":"Machine Learning","optional":false},{"name":"Physical AI","optional":false}],"status":"closed","first_seen_at":"2026-10-21T17:44:06Z","employer_posted_date":"2026-10-21","last_verified_at":"2026-10-25T17:57:56Z","board_verified":false,"closed_at":"2026-10-25T17:57:56Z","days_open":4,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":4},"description":"About the Role\nJoin an AI team developing foundation models for physical systems, with weather as an initial application. You will build the distributed infrastructure that supports large-scale model training and inference, helping advance AI for science and physical AI.\nWhat You'll Do\nDesign, deploy, and maintain distributed machine learning training and inference clusters.\n\nBuild scalable end-to-end pipelines for petabyte-scale datasets and the full model lifecycle.\n\nResearch and evaluate training approaches, including parallelization strategies and numerical precision trade-offs across model scales.\n\nProfile and debug low-level GPU operations to improve performance.\n\nAnalyze experiment results, including through ablation studies, and apply relevant research to infrastructure work.\n\nWhat We're Looking For\nTwo to ten years of experience building large-scale machine learning infrastructure for pre-trained or foundation models.\n\nHands-on experience across compute clusters, data infrastructure, distributed training, and inference, with a record of optimizing large-scale workloads.\n\nProficiency with distributed training frameworks such as FSDP or DeepSpeed, and experience with GPU performance optimization and debugging, including CUDA and JAX.\n\nKnowledge of cloud platforms such as GCP, AWS, or Azure, plus containers and orchestration tools such as Docker and Kubernetes.\n\nFamiliarity with model serving, distributed task management, and ML system monitoring, logging, observability, and version control.\n\nExperience in AI for science or physical AI, such as robotics, autonomous systems, or biology, and a generalist approach across the ML lifecycle.\n\nComfort working in fast-paced, time-sensitive environments and learning unfamiliar domains.\n\nCompensation & Benefits\nBase salary: $200,000 to $400,000 annually. Visa sponsorship is not available.\nLocation\nOn-site in San Francisco, California, United States, five days per week. Relocation support is provided.","description_format":"text","description_chars":1980,"description_truncated":false,"requirements":{"experience_years_min":2,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[{"name":"United States","iso":"US","kind":"country"}],"hiring_excludes":[],"relocation_offered":true,"industries":[],"lifecycle":[{"event":"open","at":"2026-10-21T19:31:37Z"},{"event":"close","at":"2026-10-25T17:57:56Z"}],"visa":[],"liveness":null,"pay":{"stated_usd_annual":400000,"is_top_pay":true},"html_url":"https://alion.io/job/true-talent-solutions-partners-machine-learning-infrastructure-engineer-2","json_url":"https://alion.io/job/true-talent-solutions-partners-machine-learning-infrastructure-engineer-2.json","meta":{"generated_at":"2026-10-27T04:57:58Z","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":4760,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-28T00:00:00Z"}},"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-machine-learning-infrastructure-engineer-2"},{"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-machine-learning-infrastructure-engineer-2"},{"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-machine-learning-infrastructure-engineer-2"},{"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-machine-learning-infrastructure-engineer-2\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Ftrue-talent-solutions-partners-machine-learning-infrastructure-engineer-2"}]}