Modal
Member of Technical Staff - Inference Runtime
San Francisco. Posted a month ago
The role
You will build production runtime infrastructure in Rust and Go. You will work on the container runtime stack to support inference and training workloads across the fleet.
What you will do
- Make container startup, checkpoint, and restore faster for large workloads
- Build multi-GPU and accelerator-aware snapshotting
- Design zero-copy and low-copy data paths
- Optimize large snapshot pipelines
- Improve container image and filesystem performance
- Extend sandboxed runtime to support new GPUs, drivers, and device capabilities
- Debug complex failures involving system calls, virtual memory, and kernel behavior
- Roll out runtime and kernel changes across a heterogeneous fleet
- Work across the runtime, scheduler, storage, and GPU infrastructure
Required qualifications
- Strong Linux systems knowledge, particularly processes, virtual memory, filesystems, system calls, scheduling, namespaces, cgroups, and signals
- Experience building or debugging container runtimes, sandboxes, the Linux kernel, or similarly low-level infrastructure
- Strong programming ability in Rust, Go, or another systems language
- Experience profiling and improving systems where memory movement, I/O, synchronization, or kernel interactions dominate performance
- Comfort debugging across abstraction boundaries from application behavior down to drivers and the kernel
- Ability to turn loosely defined production problems into well-designed, reliable systems
Nice to have
- gVisor, runsc, runc, OCI runtimes, seccomp, or checkpoint/restore systems
- Linux kernel development, virtualization, sandboxing, kernel modules, or device proxying
- CUDA, ROCm, GPU drivers, accelerator virtualization, or GPU profiling
- RDMA and high-performance networking
- FUSE, EROFS, direct I/O, mmap, page-cache behavior, or storage engines
- Large-memory or multi-GPU inference and training systems
- Contributions to open-source systems software
About the company
Modal is building a new infrastructure layer for AI. Their customers include companies like Ramp, Cognition, DoorDash, and Suno.