Distributed Systems Engineer (L5 + L6), Compute Runtime

At Netflix, our mission is to entertain the world. Together, we are writing the next episode - pushing the boundaries of storytelling, global fandom and making the unimaginable a reality. We are a dream team obsessed with the uncomfortable excitement of discovering what happens when you merge creativity, intuition and cutting-edge technology. Come be a part of what’s next. The Opportunity: The Cloud Infrastructure Organization’s mission is to increase the fleet-wide agility, scalability, reliability, and efficiency of our Platform. We are responsible for one of the largest Cloud Compute footprints built on AWS and constantly seeking to push boundaries through innovation to delight hundreds of millions of Netflix users daily. We are seeking a passionate engineer to join the team responsible for developing and maintaining the software that runs on our compute fleet. The team owns the Kubernetes data plane software; the container runtime; the way we download and run containers; and maintaining the underlying compute node’s operating system. The team is responsible for enabling containers to run on our compute nodes as efficiently and reliably as possible. The team partners with other teams within Netflix to ensure we are staying ahead of the needs of the business and enabling other teams to innovate on top of our platform. You will be joining a team of stunning engineers who tackle some of the largest cloud compute challenges in the industry. You will have a direct line of sight between the work you do and the entertainment of our 300M+ members. This team provides the foundational infrastructure that drives almost all computing at Netflix. The infrastructure enables Netflix’s website, video playback, video encoding work, AI/ML workloads, and numerous other business-critical functions. We free every engineer to have an impact in our “context, not control” culture and to directly contribute to the success of Netflix’s business. Some examples of the team’s work can be found in tech blogs on “noisy neighbor” detection and mount lock contention . What you will do: Build and maintain the software that runs our Kubernetes container orchestration platform Architect and design innovative solutions to support new workloads and features, and improve the reliability and performance of existing workloads Develop and maintain Kubernetes and containerd customizations and plugins Contribute to the upstream containerd and Kubernetes projects Debug performance and operational problems observed with container workloads Continuously and proactively increase efficiency and optimize our compute platform What we are looking for: Minimum of 5 years of experience evolving Compute infrastructure for a large organization; total 8+ years of software development experience Experience supporting containers and related runtimes as a service (e.g. Kubernetes kubelet, containerd, runc, NRI plugins, etc.) Experience debugging system performance issues in a Linux environment Excellent operational and troubleshooting skills Experience designing large-scale distributed systems, preferably a compute orchestration system like Kubernetes Proficiency in Go, Java, or C/C++ Understanding of networking concepts (TCP, IPv4, sockets, host and service networking in a containerized environment) Ability to thrive in ambiguity in a “context not control” environment while working with high velocity Excellent communication and collaboration skills Additionally, while not required, the following experience is also helpful: Track record of successful contributions to open source projects Linux kernel development experience Experience managing compute infrastructure for AI/ML workloads Understanding of networking concepts (TCP, IPv4, sockets, host and service networking in a containerized environment) Generally, our compensation structure consists solely of an annual salary; we do not have bonuses. You choose each year how much of your ... (truncated, view full listing at source)