{"id":105773,"url":"https://alion.io/job/zoox-staff-software-engineer-hpc","title":"Staff Software Engineer, HPC","company":{"id":3626,"name":"Zoox","domain":"zoox.com","url":"https://alion.io/company/zoox","size_band":"1001-5000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Lever","truth_index":{"grade":"B","score":72,"open_postings":43,"ghost_share":0,"stale_share":0.907,"repost_share":0,"time_to_fill_p50_days":85,"computed_at":"2026-10-19T05:45:15Z"}},"role":"Backend","role_family":"Backend","seniority":"staff","employment_type":"full_time","work_mode":"hybrid","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Foster City, United States","Seattle, United States","Boston, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":201000,"max":315000,"currency":"USD","period":"year","gross":null,"usd_annual":315000},"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AWS","optional":false},{"name":"HPC","optional":false},{"name":"Kubernetes","optional":false},{"name":"Machine Learning","optional":false},{"name":"Python","optional":false},{"name":"Ray","optional":false},{"name":"SLURM","optional":false}],"status":"live","first_seen_at":"2026-08-10T18:50:33Z","employer_posted_date":"2026-08-10","last_verified_at":"2026-10-19T04:39:27Z","board_verified":true,"closed_at":null,"days_open":69,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":69},"description":"Zoox is looking for an experienced Staff Software Engineer to build, scale, and operate our custom High-Performance Computing infrastructure. As Zoox scales its autonomous vehicle development, our HPC platform must keep pace with rapidly growing compute, storage, and scheduling demands across the company. You will modernize our HPC platform-built on industry-leading technologies like Ray.io, SLURM, and Kubernetes-with a focus on reliability, scalability, and world-class developer velocity.\nThese HPC services form the backbone of development workflows across all Zoox software teams, from data engineering to training our AI models in Perception, Planner, Prediction, to Simulation, and more. You will have a direct impact on the productivity and effectiveness of every engineering team at Zoox.\nThe position comes with a high degree of independence and the opportunity to define Zoox's HPC platform strategy, both technically and organizationally. You will work closely with stakeholders in Autonomy and Software teams to understand their workload requirements and translate them into robust, scalable infrastructure.\nIn this role, you will:\nDesign and implement core services and abstractions for distributed compute infrastructure supporting hundreds of thousands of concurrent jobs\n\nWork with customer teams and other infrastructure teams to build a multiyear software engineering roadmap for the HPC platform\n\nLead multi-quarter, cross team initiatives that drive org-wide improvements\n\nCreate production-grade APIs, SDKs, and tools that make it easy for engineers across Zoox to run large-scale distributed workloads\n\nDesign and improve job scheduling algorithms and auto-scaling policies to maximize reliability and resource availability\n\nDesign multi-region orchestration strategies that optimize for data locality, reliability, and performance\n\nIdentify and resolve systemic reliability and performance issues through profiling, analysis, and collaboration with workload owners across multiple teams\n\nEvaluate new technologies and paradigms that improve Zoox's computational and storage capabilities\n\nDevelop capacity planning tools and forecasting models to support Zoox's growing compute needs\n\nMentor junior engineers, guiding them through their career development\n\nQualifications\nExperience designing and operating large-scale distributed systems in production\n\nExperience with Ray.io, particularly Ray Core and Ray Data (or equivalent technologies)\n\nExperience with Kubernetes, particularly for heterogeneous workloads\n\nExperience with cloud infrastructure on AWS or similar providers\n\nTrack record of shipping and operating reliable, highly available scalable infrastructure\n\nDemonstrated ability to prioritize development work and build cross-functional consensus around technical tradeoffs\n\nProficiency with Python\n\nBonus Qualifications\nExposure to machine learning workloads (training, inference, data generation)\n\nExperience with Kubernetes or SLURM at scale (>10k+ nodes)\n\nExperience with SLURM workload manager and advanced scheduling policies\n\nBackground in algorithmic optimization or operations research\n\nExperience building developer tools and platforms used by large engineering organizations","description_format":"text","description_chars":3223,"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":[{"name":"United States","iso":"US","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Autonomous Driving","Smart Mobility","Automotive Manufacturing","Ride Hailing"],"lifecycle":[{"event":"open","at":"2026-08-10T18:50:33Z"}],"visa":[{"country":"US","licensed_sponsor":true,"evidence":"H-1B filings in 12 months: 373 · green card filings: 120","filings_12m":373,"filings_prev_12m":311,"green_card_filings_12m":120,"median_offered_wage_usd":181283,"route":null,"cap_exempt":false,"checked_at":"2026-10-15T11:24:14+00:00","sources":["US Department of Labor: LCA disclosure data (H-1B, H-1B1, E-3)","US Department of Labor: PERM disclosure data (green cards)"],"filings_for_role_12m":167}],"liveness":{"score":35,"band":"fade","label":"Fading","p_open":1,"p_active":0.588,"p_room":0.6,"age_days":69,"expected_fill_days":85,"reasons":["conf:1","stale_co","velocity","win:late","crowd:brand"],"computed_at":"2026-10-19T05:45:15Z"},"pay":{"stated_usd_annual":315000,"is_top_pay":true},"html_url":"https://alion.io/job/zoox-staff-software-engineer-hpc","json_url":"https://alion.io/job/zoox-staff-software-engineer-hpc.json","meta":{"generated_at":"2026-10-19T06:19:34Z","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":3888,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-20T00:00:00Z"}},"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":3626},"rest":"https://alion.io/mcp/rest/get_company?id=3626"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fzoox-staff-software-engineer-hpc"},{"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%2Fzoox-staff-software-engineer-hpc"},{"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%2Fzoox-staff-software-engineer-hpc"},{"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/zoox-staff-software-engineer-hpc\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fzoox-staff-software-engineer-hpc"}]}