Site Reliability Engineer – GenAI / AI Platforms
Equinix (company site, opens in a new tab)2–4 yrsBengaluruOn-siteDirect career pageEst. 12–22 LPA
Posted 4d ago
Reach people at Equinix
People at this company you can reach
Log in to see who works here
Create a free account or log in to see the people at Equinix you could write to:
- Recruiters & HR
- People in this function
- Work addresses
Your match
Against your primary resume
Log in to see your match score
Create a free account or log in to unlock your CV match score across:
- Role fit
- Experience
- Industry relevance
Protocol Intelligence
How competitive this role is
Competition
Background fit
Strictness
Log in to see why each signal reads the way it does.
Job description
Structured overview of role & requirements
About This Role
- Build reliability into GenAI products and platforms through resilience automation, Kubernetes hardening, capacity planning, recovery testing, and failure-injection exercises.
- Define and track service-level objectives; instrument services and build actionable monitoring, alerting, and tracing across agent, tool, and model calls.
- Support releases and on-call incident response, then drive fixes and automation from post-incident reviews; maintain reliability of self-hosted models and model-provider integrations.
Minimum Requirements
- Work Experience Required: 2–4 years in site reliability, DevOps, platform, or software engineering, with hands-on production-systems experience.
- Bachelor’s degree in computer science, engineering, or a related field, or equivalent experience.
- Proficiency in Python or Go; experience with Linux, containers, Kubernetes, a major cloud platform, CI/CD, and infrastructure as code.
- Working knowledge of monitoring, logging, tracing, alerting, distributed-system resilience, and incident response; must be willing to join an on-call rotation. Familiarity with LLM applications is required.
Ideal Candidate Profile
- Has operated GenAI or ML systems in production, including managed model platforms or self-hosted model serving, and understands latency, quotas, GPU capacity, and cost risks.
- Can connect reliability work across application, model, data, pipeline, and infrastructure layers, and turn incidents or recurring operational tasks into lasting fixes and automation.
- Experience with tools and practices such as OpenTelemetry, Prometheus/Grafana, GitOps, Helm, canary releases, load testing, or chaos engineering is a shortlist advantage.