AI Platform SRE

About

AI Platform SRE

Responsibilities

• Own end-to-end delivery of major platform initiatives—from architecture and design through deployment and post-launch optimization
• Lead deep technical ownership of Kubernetes environments, including cluster management, networking, operators, container lifecycle, and multi-tenant orchestration
• Design and build scalable, reliable distributed systems and cloud-native infrastructure on AWS and/or GCP
• Drive engineering excellence through code quality, design reviews, automation, and CI/CD best practices
• Collaborate cross-functionally with Product, AI, and Security teams to align technical solutions with business objectives
• Mentor engineers and guide architectural decisions, trade-offs, and delivery approaches
• Partner with leadership to shape engineering strategy, roadmap planning, and platform evolution

Required Qualifications

• 9+ years of experience in software engineering, with a strong focus on backend systems and infrastructure
• Proficiency in Python and/or Go, with a track record of delivering production-grade systems
• Deep, hands-on experience with Kubernetes, including building and operating clusters in production environments
• Proven expertise in designing and managing distributed systems at scale
• Strong experience with cloud platforms (AWS and/or GCP), including compute, networking, storage, and IAM
• Experience with Infrastructure as Code (Terraform or similar) and CI/CD pipelines
• Familiarity with applied AI tools and ecosystems, such as agent frameworks, AI gateways, or models like Claude and LiteLLM
• Strong system design skills and architectural decision-making capability
• Excellent communication and collaboration skills across engineering, product, and security teams

Preferred Qualifications

• Experience with observability tools such as Prometheus, Grafana, Datadog, and OpenTelemetry
• Exposure to multi-cloud or hybrid infrastructure environments
• Knowledge of API gateways, AI gateways, and policy frameworks (e.g., ABAC, OPA)
• Experience in service mesh architectures or platform-as-a-service design
• Demonstrated ability to improve engineering productivity and operational efficiency at scale