Runtime Engineer

What MatX is Building

MatX is building custom silicon for large-language-model inference and training, with HW/SW co-design across ISA, RTL, simulator, compiler, and kernels so each layer benefits from the others. The runtime owns the host-side stack and the contracts that bind those teams together.

What You'll Do Here Build the host-side interface library — device memory management, DMA, streams and events, sync primitives — that every compiler-emitted program runs on top ofOwn and extend the executable format: the compilerruntime 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

Who You Are 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, pybind
11, 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'sHands-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 launchML-systems literate — comfortable with the training and inference loop, what collectives do, what a tensor layout is.

Research depth not required.

Bonus Points If You HaveLLM 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 workML 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 Compensation

The US base salary for this full-time position is determined based on a variety of factors including role, experience, location, job-related skills, and relevant education and training. Career length is only a guideline for compensation.

Early Career - $160,000 - $250,000 + equity

Mid Career - $175,000 - $362,500 + equity

Senior Career - $250,000 - $475,000 + equity

What We Offer Time off: 4 weeks PTO (accrued) + 12 company Holidays + up to 3 weeks remote work Health:
Company-subsidized Medical (Kaiser or Anthem) for employees & dependents, Guardian Dental and Vision insurances for employee & dependents, and life insurance (employee only), plus HSA and FSA offerings via Lively. Financial Wellbeing:
Choose from Roth IRA or 401K (or both) retirement plans with up to 5% company contribution to 401K (even if you don't contribute). Also, 100% company-paid life insurance (up to $300K) and long-term disability insurances.

Professional Development: $1500 Professional Development Budget (per…