Member of Technical Staff - Inference Runtime

Modal is building the infrastructure layer for AI workloads. The Inference Runtime team owns the container runtime stack for running inference and training across the fleet. This role involves building production runtime infrastructure in Rust and Go, optimizing container startup, checkpoint/restore, multi-GPU snapshotting, and debugging complex systems issues. The work directly impacts inference performance and cold starts.

Strong Linux systems knowledge (processes, virtual memory, filesystems, system calls, scheduling, namespaces, cgroups, signals). Experience building or debugging container runtimes, sandboxes, or low-level infrastructure. Strong programming in Rust, Go, or similar. Ability to profile and improve systems where memory movement, I/O, synchronization dominate. Comfortable debugging across abstraction boundaries. Ability to turn production problems into reliable systems. Ownership of important and to