Senior Software Engineer, AI Compute Scheduling

Job Description

Design, build, and operate scheduling systems for large GPU fleets using Slurm and Kubernetes, including queueing, topology-aware placement, fair sharing, quotas, preemption, and reservations. Improve GPU utilization and service reliability, build supporting orchestration and APIs, and contribute to open-source projects while collaborating with platform and research teams.

Requirements: Requires a bachelor's or master's degree in a relevant engineering or computer science field, or equivalent experience, and at least six years building production systems software. Candidates need deep experience with a batch or cluster scheduler, strong Go, C, or C++ programming plus Python, hands-on Kubernetes and Linux expertise, and a record of improving production services.

Key Skills: Go, C, C++, Python, Slurm, Kubernetes, Kueue, Batch Scheduling, Cluster Scheduling, Linux Systems, Containers, Cgroups, GPU Scheduling, Topology-Aware Placement, Production Reliability, Workflow Orchestration

Benefits: Equity, Benefits