Staff Software Engineer, Infrastructure

MasterClass is the streaming platform where the world’s best come together to share their knowledge and stories. They are seeking a Staff Infrastructure Engineer who will act as a technical leader, designing scalable systems and enhancing infrastructure across the company. This role involves leading cloud infrastructure initiatives, partnering with various teams, and providing technical direction for infrastructure systems.

Responsibilities:

• Set technical direction for core infrastructure systems, balancing reliability, scalability, security, and developer velocity
• Design and lead implementation of complex, cross-team infrastructure initiatives (AWS, EKS, CI/CD, shared platforms)
• Build production-grade software to power infrastructure automation, tooling, and internal platforms
• Drive org-wide improvements in observability, incident response, reliability engineering, and cost efficiency
• Lead video infrastructure initiatives to evolve video delivery and CDN strategies for global scale and performance
• Partner with AI and Data teams to define and build GPU-powered infrastructure, model-serving platforms, and GenAI inference/training workflows
• Act as a technical mentor and reviewer, raising the bar for infrastructure design and operational excellence across teams
• Lead by example during incidents, postmortems, and critical architectural decisions

Requirements:

• 10+ years building and operating cloud-native production systems
• Strong expertise in: AWS architecture and large-scale cloud operations
• Strong expertise in: Kubernetes / EKS (networking, RBAC, Helm, autoscaling, cluster-level debugging)
• Strong expertise in: Infrastructure as Code (Terraform preferred)
• Strong expertise in: CI/CD and automation (GitHub Actions, Argo, or similar)
• Proven ability to design and build infrastructure software, not just operate systems
• Deep understanding of distributed systems, networking, Linux internals, and cloud security
• A track record of driving step-function improvements in reliability, scalability, or developer experience
• Strong written and verbal communication skills; able to influence technical decisions across teams
• AI/ML infrastructure, GPU scheduling, or distributed training
• Model serving frameworks (e.g., Triton, vLLM, TensorRT-LLM)
• Infrastructure autoscaling strategies, including application workloads, databases, and GenAI workloads
• KEDA, Karpenter, service mesh, or multi-cluster architectures
• HLS/DASH packaging or video encoding pipelines