{"id":194461,"url":"https://alion.io/job/nvidia-senior-software-engineer-2","title":"Senior Software Engineer","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":80,"open_postings":775,"ghost_share":0.025,"stale_share":0.735,"repost_share":0.043,"time_to_fill_p50_days":35,"computed_at":"2026-10-22T06:10:10Z"}},"role":"Backend","role_family":"Backend","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":["Bengaluru, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":25000,"max_usd":58000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":159},"experience_years_min":10,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"AIOps","optional":false},{"name":"Anomaly Detection","optional":false},{"name":"Ansible","optional":false},{"name":"Apache Kafka","optional":false},{"name":"AutoGen","optional":false},{"name":"ClickHouse","optional":false},{"name":"Grafana","optional":false},{"name":"gRPC","optional":false},{"name":"Kubernetes","optional":false},{"name":"LangChain","optional":false},{"name":"LlamaIndex","optional":false},{"name":"Loki","optional":false},{"name":"NATS","optional":false},{"name":"OpenShift","optional":false},{"name":"OpenTelemetry","optional":false},{"name":"Prometheus","optional":false},{"name":"Python","optional":false},{"name":"Self-Healing","optional":false},{"name":"Terraform","optional":false},{"name":"VictoriaMetrics","optional":false},{"name":"VMWare","optional":false},{"name":"FastAPI","optional":true}],"status":"live","first_seen_at":"2026-08-26T00:00:00Z","employer_posted_date":"2026-08-26","last_verified_at":"2026-10-22T11:16:57Z","board_verified":true,"closed_at":null,"days_open":57,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":57},"description":"We are seeking a Senior Software Engineer with strong infrastructure expertise to design, build, and operate the next generation of our enterprise Observability, Automation, and AI-driven Reliability Platform.\nThis role will build highly scalable distributed systems and platform services spanning Storage, Compute, Network, VMware, OpenShift, and bare-metal infrastructure. The engineer will help transform infrastructure operations from reactive monitoring and manual remediation to proactive, predictive, and AI-driven autonomous operations.\nWhat You Will Be Doing:\nDesign, build, and operate distributed software platforms for enterprise observability, telemetry, automation, and infrastructure reliability at large scale.\n\nDevelop reusable platform services, APIs, automation frameworks, and control planes that enable self-service, reduce operational toil, and automate infrastructure operations across multiple engineering teams.\n\nBuild scalable telemetry and event-processing systems spanning metrics, logs, traces, events, topology, and alerts, with the performance and efficiency to process billions of infrastructure signals.\n\nBuild intelligent and AI-native reliability capabilities, including agentic workflows for anomaly detection, forecasting, root-cause analysis, automated debugging, and closed-loop remediation.\n\nDrive technical architecture and engineering direction across Storage, Compute, Network, and Platform domains, solving complex and ambiguous problems that span multiple teams.\n\nEngineer for production at scale, with strong focus on software quality, scalability, security, performance, observability, maintainability, and operational readiness.\n\nProvide technical leadership and mentorship, influence engineering standards and architecture decisions, and deliver measurable improvements in reliability, MTTR, operational toil, engineering productivity, and infrastructure efficiency.\n\nWhat We Need To See:\nBachelor's or Master's degree in Computer Science, Engineering, or equivalent practical experience, with 10+ years of software engineering, SRE, infrastructure, or distributed-systems experience and demonstrated technical leadership.\n\nStrong software engineering expertise in Go, Python, or equivalent languages, with experience designing and building production-grade distributed systems, platform services, APIs, and automation.\n\nProven experience owning complex software/platform initiatives across multiple teams or infrastructure domains, from architecture and implementation through adoption and measurable impact.\n\nDeep understanding of distributed systems, event-driven architectures, microservices, APIs, and high-throughput data processing, including technologies such as Kafka, NATS, gRPC, or equivalent.\n\nStrong experience with modern observability and telemetry platforms, including OpenTelemetry, Prometheus, VictoriaMetrics, Vector, Loki, Grafana, ClickHouse, or equivalent technologies.\n\nStrong SRE and infrastructure knowledge across Kubernetes/OpenShift, VMware, bare-metal, storage, networking, and/or cloud environments, with experience using Terraform, Ansible, or equivalent automation technologies.\n\nDemonstrated ability to solve ambiguous problems, influence technical direction without direct authority, mentor engineers, establish engineering standards, and deliver measurable operational and business outcomes.\n\nWays To Stand Out From The Crowd:\nExperience building software and reliability platforms for large-scale on-premises infrastructure, particularly Storage, Compute, Networking, VMware, and Kubernetes/OpenShift.\n\nDeep understanding of storage and infrastructure telemetry, including IOPS, latency, NVMe health, SAN/NAS topology, block/object storage, and infrastructure failure domains.\n\nExperience building self-healing systems, automated remediation, predictive operations, or autonomous SRE capabilities.\n\nProduction experience applying Generative AI, AIOps, LLMs, or Agentic AI to incident triage, RCA, operational intelligence, debugging, or remediation; experience with LangChain, LlamaIndex, AutoGen, or equivalent is a plus.\n\nExperience building high-performance platform services using FastAPI, gRPC, or equivalent technologies.","description_format":"text","description_chars":4212,"description_truncated":false,"requirements":{"experience_years_min":10,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"bachelor","optional":true},"security_clearance":false,"languages":[]},"benefits":[],"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":"2026-09-03T07:23:19Z"}],"visa":[],"liveness":{"score":20,"band":"cold","label":"Long shot","p_open":1,"p_active":0.563,"p_room":0.36,"age_days":57,"expected_fill_days":35,"reasons":["conf:1","stale_co","wave","velocity","win:tail","crowd:brand"],"computed_at":"2026-10-22T06:10:10Z"},"pay":null,"html_url":"https://alion.io/job/nvidia-senior-software-engineer-2","json_url":"https://alion.io/job/nvidia-senior-software-engineer-2.json","meta":{"generated_at":"2026-10-22T13:06:44Z","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":12009,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-23T00:00:00Z"}},"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":6},"rest":"https://alion.io/mcp/rest/get_company?id=6"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fnvidia-senior-software-engineer-2"},{"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%2Fnvidia-senior-software-engineer-2"},{"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%2Fnvidia-senior-software-engineer-2"},{"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-software-engineer-2\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fnvidia-senior-software-engineer-2"}]}