E

Efficient Computer

Energy-efficient processors for edge IoT computing

Senior Staff Software Engineer - Linux Runtime & Drivers

Systems Software EngineeringConfirmed live in the last 24 hours
Full-timeIn-person

About the Job

Requirements

  • A B.S. in Electrical Engineering, Computer Engineering, or Computer Science, or equivalent; an M.S. is a plus.
  • At least 7 years of systems software experience, including significant hands-on Linux user-mode driver and language runtime library development for accelerators such as GPUs, NPUs, DSPs, or FPGAs.
  • Experience building or contributing to a production accelerator runtime software stack from the driver API through the user-facing runtime library.
  • Solid understanding of accelerator memory models, particularly unified memory systems, allocators, and zero-copy data paths.
  • Experience designing public APIs exposed by runtime libraries, including ABI stability, versioning, error models, thread safety, and documentation.
  • Experience working with compiler teams on binary formats, loaders, launch ABIs, and kernel metadata for ahead-of-time or just-in-time compilation.
  • Experience integrating runtimes with language runtimes or machine learning frameworks, including Python bindings, framework backends or execution providers, and C/C++ application interfaces.
  • Hands-on experience with QEMU, emulation, or simulation environments during pre-silicon development.
  • Experience designing interfaces between kernel and user space, including ABI and HAL design, synchronization, memory sharing, and error handling.
  • Strong user-mode debugging skills across crash analysis, sanitizers, tracing, profiling, and race and synchronization diagnosis.
  • Working knowledge of ARM/AArch64 Linux systems and the Linux driver model.
  • Expertise in C and C++, strong Python skills, and comfort using AI-assisted development tools for code, analysis, and debugging.

Responsibilities

  • Design, implement, and maintain the user-mode runtime driver for the Fabric accelerator, a shared library between the compiler and Fabric ABI. The library handles context management, program loading, resource management, command queue construction and submission, descriptor allocation and setup, streaming, completion queue and event synchronization, error handling, logging, memory allocation, and general library support.
  • Design and implement all user-mode interfaces between the compiler, the Fabric ABI, and the kernel-mode driver.
  • Define the in-memory representations generated by the compiler and consumed by the Fabric.
  • Design and implement runtime library support and interfaces for third-party machine learning framework backends used by PyTorch, ONNX, and/or TensorFlow.
  • Lead user-mode efforts to bring up first silicon, using functional simulation, emulation, and FPGA environments.
  • Establish runtime test coverage, including API unit and conformance tests, emulation-based regression suites, performance benchmarks, and hardware-in-the-loop validation.
  • Work closely with the compiler, kernel driver, architecture, micro-architecture, and verification teams throughout all phases of development.

Desired Qualifications

  • Experience contributing to CUDA Runtime (cudart), ROCm (HIP, ROCr, HSA), the Tenstorrent runtime (TT-Metalium), oneAPI Level Zero, OpenCL, or another accelerator runtime software stack.
  • Familiarity with LLVM or MLIR and with how accelerator compilers hand off to runtimes.
  • Knowledge of dataflow, spatial, or other novel compute architectures and how compilers and runtimes target them.
  • Experience on a first-generation silicon product where the software stack and hardware matured together.
  • Experience with FPGA prototyping and hardware emulation platforms such as Palladium, Zebu, or Veloce.

About the Company

Efficient Computer

Energy-efficient processors for edge IoT computing

Efficient Computer makes energy-efficient programmable processors for IoT edge devices and sells a compatible software toolchain that fits existing embedded languages and AI/ML workflows. These processors run local computations at the edge, reducing the need to send data over wireless links, which saves power and enables real-time processing and data compression. Its strength comes from combining hardware with a developer-friendly ecosystem rather than relying on general-purpose chips, helping deployments last longer in places without wired power. Its goal is to enable widespread, cost-effective edge deployments by dramatically lowering energy use and total cost of ownership for IoT networks.

Company size
51-200
Company stage
Series B
Total funding
$173M
Headquarters
Pittsburgh, PA
Founded
2022

Recently Posted Jobs

Explore more opportunities at Efficient Computer

See more jobs