Runtime Engineer

MatX is building custom silicon for large-language-model inference and training, with hardware and software co-design across the stack. The Runtime Engineer builds and owns the host-side runtime, compiler interfaces, inference serving stack, and related performance, debugging, and recovery capabilities.

What you'll do:

• Build the host-side interface library — device memory management, DMA, streams and events, sync primitives — that every compiler-emitted program runs on top of
• Own and extend the executable format: the compiler→runtime contract, its versioning, the weight and quantization layouts that let compiler and runtime evolve independently
• Design the custom-kernel ABI — calling convention, sync semantics, lifecycle — and the host-side marshaling layer (DLPack, the buffer protocol, numpy) that gets Python tensors to the device
• Build Python bindings via PyO3, with a C-ABI shim as the alternative integration path for downstream consumers
• Build the LLM inference serving stack — paged KV cache, continuous batching, request scheduling, token streaming — and the cluster orchestration primitives underneath it
• Bring up interconnect topology from the host and own the failure-detection and clean-teardown path for stop-restructure-resume recovery across racks
• Design what the chip exposes to host-side profilers and debuggers — perf counters, traces, and the Python surfaces ML engineers actually use — and hit measurable performance targets on runtime overhead and serving throughput

What they're looking for:

• Strong experience in a systems programming language — Rust, C, C++, or Go — including memory management, allocator design, and FFI/ABI work
• Have built Python interop layers in production (PyO3, ctypes, pybind11, or equivalent C-ABI bridging)
• Have designed and maintained API or ABI contracts between teams — versioning, evolution, breaking-change discipline — not just consumed someone else's
• Hands-on with at least one accelerator programming model (CUDA, ROCm, oneAPI Level Zero, TPU, or comparable) — enough to reason about device memory, async execution, and kernel launch
• ML-systems literate — comfortable with the training and inference loop, what collectives do, what a tensor layout is. Research depth not required
• LLM inference internals — vLLM, TensorRT-LLM, or SGLang (paged attention, scheduler design)
• Rust at depth, including proc macros, unsafe with soundness reasoning, and complex lifetime/trait work
• Custom allocator design (slab, paged, arena) or other low-level memory work
• ML framework integration experience (PyTorch custom backends, JAX/XLA, ONNX runtime)
• Profiler or tracing infrastructure work (perfetto, Nsight, or a custom stack)
• Driver-adjacent or kernel-bypass work, or prior new-silicon bring-up

Benefits:

• 4 weeks PTO (accrued) + 12 company Holidays + up to 3 weeks remote work
• Company-subsidized Medical (Kaiser or Anthem) for employees & dependents
• Guardian Dental and Vision insurances for employee & dependents
• Life insurance (employee only)
• HSA and FSA offerings via Lively
• Choose from Roth or pre-tax 401K (or both) with a 5% company contribution (even if you don't contribute)
• 100% company-paid life insurance (up to $300K)
• Long-term disability and travel insurance
• $1500 per year Professional Development Budget
• MatX provides onsite team lunch & dinner Monday - Friday, with your choice of ordering via WeBox, Specialty’s or via our reimbursement system