{"id":1158232,"url":"https://alion.io/job/nvidia-senior-software-engineer-dgx-cloud-production-engineering-4","title":"Senior Software Engineer, DGX Cloud Production Engineering","company":{"id":6,"name":"NVIDIA","domain":"nvidia.com","url":"https://alion.io/company/nvidia","size_band":"5000+","is_staffing_agency":false,"is_intermediary":false,"ats_vendor":"Workday","truth_index":{"grade":"A","score":92,"open_postings":225,"ghost_share":0.013,"stale_share":0.244,"repost_share":0.044,"time_to_fill_p50_days":24,"computed_at":"2026-09-23T05:45:00Z"}},"role":"Backend","role_family":"Backend","seniority":"senior","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"hiring_geo_confidence":"structured","locations":["Santa Clara, United States","United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":184000,"max":287500,"currency":"USD","period":"year","gross":null,"usd_annual":287500},"salary_estimate":null,"experience_years_min":8,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"ArgoCD","optional":false},{"name":"GitOps","optional":false},{"name":"Kubernetes","optional":false},{"name":"Linux","optional":false},{"name":"Python","optional":false},{"name":"Terraform","optional":false}],"status":"live","first_seen_at":"2026-09-23T22:29:10Z","employer_posted_date":"2026-09-23","last_verified_at":"2026-09-24T01:29:10Z","board_verified":true,"closed_at":null,"days_open":0,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":0},"description":"NVIDIA DGX Cloud is building and operating large-scale GPU infrastructure for AI research and production workloads. We are looking for Senior Software Engineers to help build the automation, tooling, and operational systems that make GPU clusters reliable, scalable, and safe to run. This role is part of a production engineering team focused on Kubernetes-based infrastructure, GPU cluster operations, reliability, automation, GitOps, and Day 2 operability across DGX Cloud environments.\nWhat you’ll be doing:\nBuild and operate automation for large-scale GPU clusters across NVIDIA Cloud Partners (NCP) and on-prem environments.\nDevelop tools and services for provisioning, validation, upgrades, monitoring, repair, and cluster lifecycle operations.\nImprove Day 0 / Day 1 / Day 2 workflows for cluster bringup, handoff, and production operations.\nReduce manual production touches through APIs, GitOps, automation, and agent-assisted workflows.\nParticipate in on-call, incident response, debugging, and durable follow-up work.\nPartner with platform, storage, networking, security, and workload teams to make infrastructure production-ready.\nWhat we need to see:\n8+ years of experience building or operating production infrastructure.\nStrong programming skills in Python, Go, or similar.\nExperience with Linux, Kubernetes, containers, cloud infrastructure, or infrastructure automation.\nAbility to troubleshoot distributed systems in production.\nClear communication and ability to work across teams.\nBS/MS in Computer Science or equivalent experience.\nWays to stand out from the crowd:\nExperience with GPU infrastructure, Kubernetes operators, GitOps, Terraform, ArgoCD, or fleet automation.\nExperience with SLOs, on-call, incident response, observability, and reliability practices.\nExposure to BMaaS, VMaaS, managed Kubernetes, or multi-cloud infrastructure.\nNVIDIA is leading the way in groundbreaking developments in Artificial Intelligence, High-Performance Computing and Visualization. The GPU, our invention, serves as the visual cortex of modern computers and is at the heart of our products and services. We have some of the most forward-thinking and hard-working people on the planet working for us. If you're creative, hard-working and self-motivated, we want to hear from you!\nYour base salary will be determined based on your location, experience, and the pay of employees in similar positions. The base salary range is 184,000 USD - 287,500 USD for Level 4, and 224,000 USD - 356,500 USD for Level 5.You will also be eligible for equity and benefits.\nApplications for this job will be accepted at least until September 27, 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":3184,"description_truncated":false,"requirements":{"experience_years_min":8,"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":["Artificial Intelligence","Information Technology","Autonomous Driving","Computer Components"],"lifecycle":[{"event":"open","at":"2026-09-23T22:29:10Z"}],"liveness":{"score":86,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.86,"p_room":1,"age_days":0,"expected_fill_days":24,"reasons":["conf:1","win:early","comp:brand"],"computed_at":"2026-09-24T02:43:37Z"},"pay":{"stated_usd_annual":287500,"is_top_pay":true},"html_url":"https://alion.io/job/nvidia-senior-software-engineer-dgx-cloud-production-engineering-4","json_url":"https://alion.io/job/nvidia-senior-software-engineer-dgx-cloud-production-engineering-4.json","meta":{"generated_at":"2026-09-24T02:43:37Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers"}}