{"id":3905072,"url":"https://alion.io/job/nvidia-senior-system-software-engineer-dgx-cloud-ai-infrastructure","title":"Senior System Software Engineer, DGX Cloud AI Infrastructure","company":{"id":6,"name":"NVIDIA","domain":"nvidia.com","url":"https://alion.io/company/nvidia","size_band":"5000+","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Workday","truth_index":{"grade":"B","score":83,"open_postings":794,"ghost_share":0.025,"stale_share":0.594,"repost_share":0.055,"time_to_fill_p50_days":41,"computed_at":"2026-11-08T05:47:12Z"}},"role":"DevOps","role_family":"DevOps","seniority":"senior","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Santa Clara, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":224000,"max":356500,"currency":"USD","period":"year","gross":null,"usd_annual":356500},"salary_estimate":null,"experience_years_min":12,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"CI/CD","optional":false},{"name":"JAX","optional":false},{"name":"Kubernetes","optional":false},{"name":"LLM","optional":false},{"name":"PyTorch","optional":false},{"name":"Ray","optional":false},{"name":"SLURM","optional":false},{"name":"TensorFlow","optional":false}],"status":"live","first_seen_at":"2026-11-06T00:00:00Z","employer_posted_date":"2026-11-06","last_verified_at":"2026-11-08T15:40:05Z","board_verified":true,"closed_at":null,"days_open":2,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":2},"description":"NVIDIA’s DGX Cloud team builds the infrastructure behind large-scale AI training for NVIDIA’s own training workloads and for our customers. We build services, tools and open-source software that make ML workloads more efficient and resilient.\nWe’re looking for a Senior Software Engineer for the NVIDIA Recovery and Resilience team. You’ll own our AI infrastructure services, tools and open-source projects to support resilient and efficient training from design through production. You’ll also mentor engineers and decide how the team runs what it builds.\nWhat You Will Be Doing:\nDrive the design, build, launch and operation of our services, tools and open-source projects.\nPlan and assign the team’s work, mentor junior engineers and review designs.\nBuild resilient AI infrastructure on Kubernetes and Slurm for NVIDIA’s own training workloads and customer workloads. This includes supercomputers at major cloud providers and on-premises clusters.\nBuild APIs that connect to NVIDIA’s resiliency systems: telemetry, break/fix automation, and checkpoint and execution systems.\nBuild a job submission layer that hides infrastructure failures from users and restarts long-running training jobs automatically.\nBuild agentic tools that help customers improve training efficiency by finding bottlenecks, diagnosing failures and recommending fixes.\nDrive our open-source work. Release components so customers and the community can use them, and work with them to improve those components.\nSet up how the team runs its services: support, monitoring, alerts, CI/CD, integration test gates and on-call plans.\nWhat We Need To See:\nBS, MS or PhD in Computer Science or a related field (or equivalent experience), plus 12+ years of experience.\nProven experience who has taken large systems from design through production.\nStrong experience with Kubernetes and/or Slurm at scale.\nHands-on experience with PyTorch, TensorFlow, JAX or Ray.\nStrong understanding of NVIDIA GPUs and networking, including how they fail.\nExperience running production services, including CI/CD, monitoring, alerting and on-call.\nWays to Stand Out from the Crowd:\nHands-on experience with fault tolerance or checkpointing for large-scale distributed training on GPU supercomputers.\nDemonstrated experience building LLM-based agents or AI tools for performance analysis or troubleshooting.\nBackground in building external services or maintaining open-source projects in ML infrastructure.\nYour base salary will be determined based on your location, experience, and other objective job-related factors. The expected base salary ranges for this position are:224,000 USD - 356,500 USD for Level 5; and 272,000 USD - 431,250 USD for Level 6.\nYou will also be eligible for equity and benefits.\nApplications for this job will be accepted at least until November 10, 2026.This posting is for an existing vacancy.\nNVIDIA uses AI tools in its recruiting processes.\nNVIDIA is committed to fostering an inclusive work environment and proud to be an equal opportunity employer. As we highly value diversity in our current and future employees, we do not discriminate (including in our hiring and promotion practices) on the basis of race, religion, color, national origin, gender, gender expression, sexual orientation, age, marital status, veteran status, disability status or any other characteristic protected by law.","description_format":"text","description_chars":3371,"description_truncated":false,"requirements":{"experience_years_min":12,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"bachelor","optional":false},"security_clearance":false,"languages":[]},"benefits":["Equity"],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Processors, MCUs & AI Chips","Servers & Data Center Hardware","Computer Components","AI Chips & Accelerators"],"lifecycle":[{"event":"open","at":"2026-11-07T02:38:34Z"}],"visa":[{"country":"US","licensed_sponsor":true,"adverts_offering_sponsorship_24m":0,"sanctioned_now":false,"evidence":"H-1B filings in 12 months: 2,856 · green card filings: 799","filings_12m":2856,"filings_prev_12m":1684,"green_card_filings_12m":799,"median_offered_wage_usd":186407,"route":null,"cap_exempt":false,"checked_at":"2026-11-08T10:45:15+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":1244}],"liveness":{"score":63,"band":"ok","label":"Likely open","p_open":1,"p_active":0.632,"p_room":1,"age_days":2,"expected_fill_days":41,"reasons":["conf:6","stale_co","velocity","win:early","comp:brand"],"computed_at":"2026-11-08T05:47:12Z"},"pay":{"stated_usd_annual":356500,"is_top_pay":true},"html_url":"https://alion.io/job/nvidia-senior-system-software-engineer-dgx-cloud-ai-infrastructure","json_url":"https://alion.io/job/nvidia-senior-system-software-engineer-dgx-cloud-ai-infrastructure.json","meta":{"generated_at":"2026-11-08T18:16:03Z","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":38327,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-09T00:00:00Z"}},"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":6},"rest":"https://alion.io/mcp/rest/get_company?id=6"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fnvidia-senior-system-software-engineer-dgx-cloud-ai-infrastructure"},{"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%2Fnvidia-senior-system-software-engineer-dgx-cloud-ai-infrastructure"},{"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%2Fnvidia-senior-system-software-engineer-dgx-cloud-ai-infrastructure"},{"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/nvidia-senior-system-software-engineer-dgx-cloud-ai-infrastructure\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fnvidia-senior-system-software-engineer-dgx-cloud-ai-infrastructure"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":3905072}},{"tool":"search_jobs","arguments":{"company":"nvidia.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":3905072},"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"}}