SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Modal's Inference Runtime team owns the container runtime stack that executes inference and training workloads across the company's fleet. This role sits at the intersection of Linux, containers, filesystems, storage, GPU drivers, and distributed systems, with the mission to make demanding ML workloads start quickly, run efficiently, and remain securely isolated.
You will build production runtime infrastructure in Rust and Go, diagnose complex Linux and performance problems, and help architect Modal's container platform. Key responsibilities include:
- Dramatically accelerate container startup, checkpoint, and restore for large inference and training workloads.
- Design multi-GPU and accelerator-aware snapshotting with efficient GPU memory and RDMA handling.
- Engineer zero-copy and low-copy data paths between container memory, filesystems, storage, and Modal's runtime.
- Optimize large snapshot pipelines using parallel uploads, direct I/O, incremental snapshots, and improved memory handling.
- Improve container image and filesystem performance across EROFS, FUSE, page caches, overlay filesystems, and remote storage.
- Extend the sandboxed runtime to support new GPUs, drivers, profiling tools, and device capabilities across NVIDIA and AMD hardware.
- Debug complex failures involving system calls, virtual memory, process lifecycle, kernel behavior, GPU drivers, and container isolation.
- Safely roll out runtime and kernel changes across a heterogeneous fleet using compatibility controls, scheduling constraints, feature flags, and observability.
- Own ambiguous production problems from investigation through deployment, working across runtime, scheduler, storage, and GPU infrastructure teams.
You will also work closely with maintainers of gVisor and contribute to the runtime itself when appropriate fixes belong upstream.
REQUIREMENTS:
- Strong Linux systems knowledge: processes, virtual memory, filesystems, system calls, scheduling, namespaces, cgroups, and signals.
- Experience building or debugging container runtimes, sandboxes, Linux kernel, or similarly low-level infrastructure.
- Strong programming ability in Rust, Go, or another systems language, with interest in becoming productive in both Rust and Go.
- Experience profiling and improving systems where memory movement, I/O, synchronization, or kernel interactions dominate performance.
- Comfort debugging across abstraction boundaries, from application behavior through runtimes, drivers, and the kernel.
- Ability to turn loosely defined production problems into well-designed, reliable systems.
- Desire to own important infrastructure and work closely with internal teams and customers.
PARTICULARLY RELEVANT (optional):
- 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.
- Open-source systems software contributions.
Prior gVisor or machine-learning experience is not required. The company prioritizes strong systems fundamentals, curiosity, and the ability to learn unfamiliar parts of the stack.
About Modal Labs
AI / Data / Infrastructure — serverless cloud platform for AI, data, and compute-intensive applications.
