{"id":3836053,"url":"https://alion.io/job/true-talent-solutions-partners-machine-learning-infrastructure-engineer-4","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":true,"has_equity":false,"technologies":[{"name":"AWS","optional":false},{"name":"Azure","optional":false},{"name":"C++","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":"Linux","optional":false},{"name":"Machine Learning","optional":false},{"name":"Python","optional":false}],"status":"live","first_seen_at":"2026-11-05T17:46:14Z","employer_posted_date":"2026-11-05","last_verified_at":"2026-11-09T05:32:27Z","board_verified":true,"closed_at":null,"days_open":3,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":3},"description":"About the Role\nJoin an AI research team building large-scale models for physical systems, with weather as an initial application. You will develop the infrastructure for distributed model training and inference, helping turn large volumes of observational data into useful predictions and insights.\nWhat You'll Do\nDesign, deploy, and maintain distributed machine learning training and inference clusters.\n\nBuild scalable pipelines for petabyte-scale datasets and manage model training across the machine learning lifecycle.\n\nTest training approaches, including parallelization methods and numerical precision trade-offs across model sizes.\n\nProfile and debug low-level GPU operations to improve performance.\n\nEvaluate research and apply relevant techniques to infrastructure and training workflows.\n\nAnalyze training experiments, including results from ablation studies, to inform model development.\n\nWhat We're Looking For\nTwo to ten years of experience building large-scale machine learning infrastructure for pretrained or foundation models.\n\nHands-on experience with compute clusters, data infrastructure, inference systems, and distributed training.\n\nStrong skills in optimizing large-scale training, data, or inference workloads, including GPU performance debugging.\n\nProficiency with distributed training frameworks such as FSDP or DeepSpeed, and experience with CUDA and JAX.\n\nExperience with Python, C++, Linux, NVIDIA GPUs, and cloud platforms such as GCP, AWS, or Azure.\n\nFamiliarity with Docker, Kubernetes, distributed task management, model serving, monitoring, logging, and observability.\n\nBackground in physical AI or AI for science, such as robotics, self-driving, or biology, and interest in mission-driven work.\n\nA generalist approach to the machine learning lifecycle and experience delivering in fast-paced, time-sensitive environments.\n\nCompensation & Benefits\nBase salary is $200,000 to $400,000 USD annually. Visa sponsorship is not available. Relocation support is provided.\nLocation\nOn-site in San Francisco, California, United States, five days per week.","description_format":"text","description_chars":2081,"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":"2026-11-05T21:06:42Z"}],"visa":[{"country":"US","licensed_sponsor":false,"adverts_offering_sponsorship_24m":96,"sanctioned_now":false,"evidence":"Offered visa sponsorship in 96 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":"2026-11-08T10:45:15+00:00","sources":["Alion: sponsorship offered in the employer's own job adverts (24 months)"],"filings_for_role_12m":0}],"liveness":{"score":35,"band":"fade","label":"Fading","p_open":1,"p_active":0.472,"p_room":0.75,"age_days":3,"expected_fill_days":4,"reasons":["conf:0","agency","velocity","win:late","comp:junior,brand"],"computed_at":"2026-11-09T06:03:00Z"},"pay":{"stated_usd_annual":400000,"is_top_pay":true},"html_url":"https://alion.io/job/true-talent-solutions-partners-machine-learning-infrastructure-engineer-4","json_url":"https://alion.io/job/true-talent-solutions-partners-machine-learning-infrastructure-engineer-4.json","meta":{"generated_at":"2026-11-09T07:28:00Z","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":4750,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-10T00:00:00Z"}},"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-machine-learning-infrastructure-engineer-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-machine-learning-infrastructure-engineer-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-machine-learning-infrastructure-engineer-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-machine-learning-infrastructure-engineer-4\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Ftrue-talent-solutions-partners-machine-learning-infrastructure-engineer-4"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":3836053}},{"tool":"search_jobs","arguments":{"company":"truetalentsolutionspartners.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":3836053},"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"}}