{"id":2026836,"url":"https://alion.io/job/p-machine-learning-infrastructure-engineer-modeling","title":"Machine Learning Infrastructure Engineer (Modeling)","company":{"id":3908685,"name":"Pi","domain":"xn--1xa.com","url":"https://alion.io/company/p-6","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Welcome to the Jungle","truth_index":{"grade":"B","score":75,"open_postings":3,"ghost_share":0,"stale_share":1,"repost_share":0,"time_to_fill_p50_days":null,"computed_at":"2026-10-10T05:45:15Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":null,"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":null,"salary_estimate":{"min_usd":164000,"max_usd":361000,"period":"year","method":"role_country_seniority_unknown","sample_n":3798},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AWS","optional":false},{"name":"GCP","optional":false},{"name":"Google GKE","optional":false},{"name":"JAX","optional":false},{"name":"Kubernetes","optional":false},{"name":"Machine Learning","optional":false},{"name":"PyTorch","optional":false},{"name":"SLURM","optional":false},{"name":"TPU","optional":false}],"status":"live","first_seen_at":"2026-09-04T00:13:33Z","employer_posted_date":"2026-10-07","last_verified_at":"2026-10-11T19:39:24Z","board_verified":true,"closed_at":null,"days_open":37,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":37},"description":"Join our ML Infrastructure team as a Machine Learning Infrastructure Engineer. You will be responsible for designing, implementing, and maintaining systems for large-scale model training, optimizing performance, and enabling rapid iteration. You will work closely with researchers to scale JAX-based training across TPU and GPU clusters and contribute to core training code. Strong software engineering fundamentals and experience in ML training infrastructure are required.\nMissions\nConception, mise en œuvre et maintenance des systèmes pour l'entraînement de modèles à grande échelle, y compris la planification, la gestion des tâches, le point de contrôle et la journalisation.\nCollaboration avec les chercheurs pour étendre l'entraînement basé sur JAX sur des clusters TPU et GPU, en minimisant les frictions.\nProfilage et amélioration de l'utilisation de la mémoire, de l'utilisation des appareils, du débit et de la synchronisation distribuée.\nProfil recherché\n - Strong software engineering fundamentals and experience building ML training infrastructure or internal platforms- Strong cross-functional communication and ownership mindset\n- Experience managing training workloads on cloud platforms (e.g., SLURM, Kubernetes, GCP TPU/GKE, AWS)\n- Familiarity with distributed training, multi-host setups, data loaders, and evaluation pipelines\n- Ability to debug and optimize performance bottlenecks across the training stack\n- Hands-on large-scale training experience in JAX (preferred), PyTorch\n- Experience designing abstractions that balance researcher flexibility with system reliability\n- Background in robotics, multimodal models, or large-scale foundation models\n- Experience operating close to hardware (GPU/TPU performance tuning)\n- Deep ML systems background (e.g., training compilers, runtime optimization, custom kernels)","description_format":"text","description_chars":1838,"description_truncated":false,"requirements":{"experience_years_min":null,"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":"2026-10-07T13:30:05Z"}],"visa":[],"liveness":{"score":23,"band":"cold","label":"Long shot","p_open":1,"p_active":0.51,"p_room":0.45,"age_days":36,"expected_fill_days":21,"reasons":["conf:0","velocity","win:tail"],"computed_at":"2026-10-10T05:45:15Z"},"pay":null,"html_url":"https://alion.io/job/p-machine-learning-infrastructure-engineer-modeling","json_url":"https://alion.io/job/p-machine-learning-infrastructure-engineer-modeling.json","meta":{"generated_at":"2026-10-11T21:47:02Z","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":10920,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-12T00:00:00Z"}},"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":3908685},"rest":"https://alion.io/mcp/rest/get_company?id=3908685"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fp-machine-learning-infrastructure-engineer-modeling"},{"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%2Fp-machine-learning-infrastructure-engineer-modeling"},{"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%2Fp-machine-learning-infrastructure-engineer-modeling"},{"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/p-machine-learning-infrastructure-engineer-modeling\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fp-machine-learning-infrastructure-engineer-modeling"}]}