Senior SRE Engineer (MLOps) - AI
Core
Operate AI and ML systems as production services, ensuring reliability, observability, and cost-effectiveness for agentic AI and generative AI features.
Role type
Senior SRE Engineer (MLOps)
Builds
Reliable inference APIs, retrieval systems, and agentic AI workflows at scale
Domain
AI/ML Operations, Generative AI, Agentic Systems
Deliverable
production ML models | infrastructure
Required skills
Kubernetes, CI/CD, GitOps, incident response, infrastructure-as-code, Python, distributed systems, observability, safe-release patterns, cost governance, prompt injection defense
Preferred skills
MLOps platforms, LLM applications, RAG, vector databases, workflow orchestration, OpenTelemetry, Prometheus, Grafana, MLflow, KServe, Ray, LiteLLM, vLLM, LangGraph, Arize Phoenix, LangSmith, Kafka, GPU workloads
Responsibilities
Own reliability for ML and agentic AI services (SLOs, dashboards, alerts), build observability across the AI stack, design safe-release patterns for models and agents, provide operational support for inference APIs and Kubernetes/EKS, establish guardrails for agent tool-calling, drive AI cost governance, build automation for safe production paths
Seniority
Senior, hands-on IC