The Technical Program Manager will support Cloud Inference, which builds and operates Kubernetes-native, cluster-level serving infrastructure for Modular's inference products. The infrastructure runs large language models in production across clouds and hardware vendors. The team owns cluster orchestration, multi-cluster routing, and the deployment path for safely releasing model and engine versions. This is a hands-on technical role between Cloud Inference and the MAX product and customer-facing teams. The program manager turns goals such as higher GPU throughput, lower cost per token, faster model bring-up, and fewer production incidents into shipped work. The role works with live customer-traffic systems, where rollout decisions directly affect latency and spending. The position partners with engineering and product leaders to structure planning, tracking, and communication; participates in design and capacity discussions; helps teams develop realistic plans; surfaces risks early; and shapes engineering decisions across the organization. Candidates may work from the Los Altos, California office or remotely from home, and new-hire onboarding takes place in person at the Los Altos office. Candidates based in or open to relocating to the United States or Canada are welcome.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
Job Type
Full-time
Career Level
Senior