AI Site Reliability Engineer

You will work across cloud infrastructure, Kubernetes, GPU compute, model-serving systems, observability, automation, and incident response. You will partner with software, data science, security, and platform teams to ensure our AI systems meet high standards for availability, latency, performance, cost, and operational safety., * Design, operate, and improve highly available infrastructure for AI training, inference, and data-processing workloads.

• Define and manage service-level objectives, reliability metrics, error budgets, and capacity plans.
• Build monitoring, logging, tracing, alerting, and AI-specific observability for model-serving platforms.
• Lead incident response, root-cause analysis, post-incident reviews, and reliability improvements.
• Automate deployment, scaling, rollback, disaster recovery, and routine operational tasks.
• Operate Kubernetes-based services, cloud platforms, GPU clusters, networking, storage, and CI/CD systems.
• Improve model-serving performance, including latency, throughput, GPU utilization, availability, and cost efficiency.
• Develop safe automation and self-healing workflows for common production issues.
• Establish operational standards for model versioning, rollouts, canary releases, feature flags, and rollback procedures.
• Collaborate with engineering and ML teams to make AI systems production-ready.
• Maintain clear runbooks, architecture documentation, and operational procedures.
• Participate in an on-call rotation and help build a sustainable, low-noise operational culture.

• 4+ years of experience in SRE, infrastructure engineering, DevOps, platform engineering, or production engineering.
• Strong Linux, networking, cloud, and distributed-systems experience.
• Hands-on experience with Kubernetes and infrastructure-as-code tools such as Terraform.
• Experience with at least one major cloud platform: AWS, Azure, or Google Cloud.
• Proficiency in Python, Go, or another programming language used for automation and production systems.
• Experience with observability platforms, metrics, logs, traces, and incident-management practices.
• Experience operating production services with defined availability and performance targets.
• Strong troubleshooting, communication, documentation, and systems-thinking skills., * Experience operating machine-learning or generative-AI workloads in production.
• Familiarity with GPUs, CUDA, model-serving systems, vector databases, or high-performance computing.
• Experience with tools such as Prometheus, Grafana, OpenTelemetry, Argo CD, Helm, or service meshes.
• Knowledge of MLOps practices, model lifecycle management, and ML/data pipelines.
• Experience with reliability testing, chaos engineering, load testing, or capacity modeling.
• Understanding of AI security, data privacy, model-safety controls, and access management.