{"id":3992419,"url":"https://alion.io/job/nvidia-senior-engineer-dgx-cloud-resilience-engineering-data-platform","title":"Senior Engineer, DGX Cloud Resilience Engineering - Data Platform","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":84,"open_postings":797,"ghost_share":0.025,"stale_share":0.55,"repost_share":0.055,"time_to_fill_p50_days":41,"computed_at":"2026-11-09T06:03:00Z"}},"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","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":7,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Agentic Workflows","optional":false},{"name":"AI Agents","optional":false},{"name":"Databricks","optional":false},{"name":"Delta Lake","optional":false},{"name":"PagerDuty","optional":false},{"name":"Python","optional":false},{"name":"SLI/SLO/SLA","optional":false}],"status":"live","first_seen_at":"2026-11-09T23:50:51Z","employer_posted_date":"2026-11-09","last_verified_at":"2026-11-09T23:50:51Z","board_verified":true,"closed_at":null,"days_open":0,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":0},"description":"Join a team of engineers at NVIDIA dedicated to building the operational data foundation that powers reliability and resiliency across the DGX Cloud program. Our team designs and operates the data platforms, pipelines, and schemas that enable engineering and leadership teams to measure, understand, and improve operational excellence at scale. As the DGX Cloud program grows, enabling teams to develop, deploy, and manage accelerated computing infrastructure is a top priority, and this team sits at the center of that mission.\nWhat you’ll be doing:\nOwn and operate the data platform end to end, including the pipelines that ingest, transform, and serve operational data to leadership and partner teams.\nEnsure the reliability of those pipelines by setting and meeting targets for uptime, data freshness, and quality, and by leading incident response, root cause analysis, and prevention work.\nDefine, instrument, and report on operational success metrics such as SLIs/SLOs, pipeline latency, and data completeness, and use them to drive prioritization and continuous improvement.\nPartner with customer teams to understand their data needs, translate those needs into platform capabilities and schemas, and set clear expectations for support and delivery.\nProvide technical leadership by setting engineering standards, reviewing designs and code, mentoring engineers, and driving the platform roadmap.\nWhat we need to see:\n7+ years of experience in software technical leadership roles in an agile software development environment.\nBS in Computer Science, Engineering, or a related field, or equivalent experience.\nConfirmed experience owning and operating production data pipelines, with a track record of keeping them reliable, observable, and fresh.\nHands-on expertise in Databricks, including designing and leading schemas, tables, and access patterns using Delta Lake.\nStrong Python skills, with experience building maintainable, well-tested, production-grade data code.\nSolid understanding of medallion architecture and data modeling practices, with the judgment to apply them to balance data quality, performance, and usability.\nExperience applying data lineage, retention, and access policies in production environments.\nWays to stand out from the crowd:\nExperience building data products and tooling that enables agentic workflows and analysis.\nExperience working with APIs for operational data including PagerDuty, Rootly, and Backstage.\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:\n184,000 USD - 287,500 USD for Level 4; and 224,000 USD - 356,500 USD for Level 5.\nYou will also be eligible for equity and benefits.\nApplications for this job will be accepted at least until November 13, 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":3368,"description_truncated":false,"requirements":{"experience_years_min":7,"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":"2026-11-09T23:50:51Z"}],"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":"2026-11-09T07:32:21+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":86,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.86,"p_room":1,"age_days":0,"expected_fill_days":41,"reasons":["conf:2","win:early","comp:brand"],"computed_at":"2026-11-10T01:51:58Z"},"pay":{"stated_usd_annual":287500,"is_top_pay":true},"html_url":"https://alion.io/job/nvidia-senior-engineer-dgx-cloud-resilience-engineering-data-platform","json_url":"https://alion.io/job/nvidia-senior-engineer-dgx-cloud-resilience-engineering-data-platform.json","meta":{"generated_at":"2026-11-10T01:51:58Z","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":4324,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-11T00:00:00Z"}},"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-engineer-dgx-cloud-resilience-engineering-data-platform"},{"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-engineer-dgx-cloud-resilience-engineering-data-platform"},{"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-engineer-dgx-cloud-resilience-engineering-data-platform"},{"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-engineer-dgx-cloud-resilience-engineering-data-platform\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fnvidia-senior-engineer-dgx-cloud-resilience-engineering-data-platform"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":3992419}},{"tool":"search_jobs","arguments":{"company":"nvidia.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":3992419},"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"}}