← All roles

Senior Site Reliability Engineer (Noida, BLR, India)

Level AI· Engineering
Apply on company site
Hybrid (Noida, Bengaluru)Full-timePosted 4mo ago

About the role

Senior SRE role at Level AI blending backend engineering, infrastructure operations, and FinOps. Focus on cost efficiency, GPU throughput, reliability instrumentation, and enabling backend teams to own cost and reliability budgets in a hybrid on-premise/cloud environment.

Responsibilities

  • Infrastructure cost efficiency and FinOps. Own the continued reduction of Kubernetes overprovisioning, drive right-sizing programs, and maintain the cost telemetry that backend teams use to make decisions.
  • GPU throughput optimization. Run a structured experimentation program on on-premise GPU clusters, partnering with AI service owners. Lead by the Engineering leadership, with this role providing the experimental bandwidth.
  • Backend enablement, not ownership absorption. Build the tooling, dashboards, and processes that let backend teams from other groups own their own cost and reliability budgets. The deliverable is leverage, not headcount-shaped work.
  • Reliability instrumentation. As the infra team owns most of the instrumentation across new and offline flows, this role takes a central seat in making sure that surface area is captured properly for both cost-at-scale and reliability.
  • Selective security workstreams. Take on a defined slice of the active security work so that senior DevOps engineers are not the single point of execution for security-adjacent platform changes.

Qualifications

  • 4-5 years of hands-on systems experience.
  • Backend engineering depth: production experience in Python, Go/Rust, capable of owning services end to end.
  • Kubernetes at scale: scheduler behavior, resource requests/limits, HPA/VPA, node pool design, cost-aware autoscaling (Cast AI, Karpenter, or equivalent).
  • Cloud and on-premise infrastructure: GCP fluency, IaC (Terraform), CI/CD, hybrid setups including on-prem GPU clusters.
  • GPU workload understanding: throughput profiling, batching, KV-cache behavior, inference server tuning, GPU utilization metrics.
  • Observability and reliability: metrics, traces, logs, SLOs, and proper instrumentation.
  • FinOps mindset: demonstrated history of converting infrastructure choices into measurable cost outcomes.
  • Security baseline: able to take on platform-security workstreams without requiring constant handoff to the DevOps team.

Skills

Required:Backend engineeringKubernetes at scaleCloud and on-premises infrastructure
Nice to have:GPU workload understanding
Last updated Aug 19, 2026. Interested? Apply on the company site.
Level AI logo

About Level AI

One AI platform for your entire Customer Experience journey

Level AI's call center AI uses semantic intelligence to understand support interactions to improve contact center team performance. Request a demo today.

Customer ExperienceAI Virtual AgentQuality AutomationVoice of the CustomerGenerative AIcustomer supportcontact center
Company profileWebsite

More open roles at Level AI