E

EdgeCortix

Energy-efficient edge AI processors and software

Compiler Software Engineer

Systems Software EngineeringConfirmed live in the last 24 hours
Full-timeKawasaki, Kanagawa, JapanHybrid

About the Job

Requirements

  • A Bachelor's degree in Computer Engineering, Computer Science, and/or Electrical Engineering is required.
  • At least 5 years of Software Engineering experience is required.
  • At least 3 years of experience writing production-quality C++ is required.
  • At least 2 years of experience developing Python, including pip packaging and C++ bindings, is required.
  • At least 2 years of experience with machine-learning graph optimization passes is required.
  • At least 1 year of experience using the MLIR/LLVM framework is required.
  • Experience with code management using Git and familiarity with GitHub/GitLab pull-request workflows are required.
  • Exposure to continuous integration and continuous delivery tools such as Jenkins is required.
  • Knowledge of machine-learning quantization techniques and mixed-precision inference is required.
  • Strong debugging and analysis skills for root-causing complex issues are required.

Responsibilities

  • Extend the compiler and software toolchain for deploying machine-learning models with high performance and flexibility on the company's proprietary AI hardware accelerator.
  • Work closely with hardware and machine-learning engineers.

Desired Qualifications

  • Knowledge of neural networks and hands-on experience using machine-learning frameworks such as TensorFlow, PyTorch, or ONNX.
  • Knowledge of convolutional neural networks, recurrent neural networks/long short-term memory networks, or transformers/large language models, and familiarity with multimodal machine-learning models.
  • Experience developing embedded software, preferably for application-specific integrated circuits or on-device machine learning.
  • Experience with low-level, machine-specific code generation such as x86 or RISC-V.
  • Familiarity with code generation for microcode, such as video codec firmware or CPU microcode.
  • Experience with vectorization and parallel programming models such as OpenMP or CUDA/OpenCL.
  • Previous experience working in an Agile environment and collaborating with multidisciplinary teams across different time zones.
  • Experience writing performance or functional simulators and interpreters.

About the Company

EdgeCortix

Energy-efficient edge AI processors and software

EdgeCortix designs energy-efficient AI accelerators and software for running machine learning workloads at the edge. Its hardware and compiler software are co-designed around the Dynamic Neural Accelerator, a reconfigurable processor that adapts to different neural networks to maximize utilization while keeping power low. It offers chips such as SAKURA-II and the upcoming SAKURA-X, plus M.2 modules, PCIe cards, and complete systems, along with the MERA software platform and MERA Studio tools to compile and deploy models from common frameworks onto its hardware. The company differentiates itself with a software-first, hardware-software co-design approach and a full edge-focused ecosystem for embedded, industrial, robotics, smart cities, and aerospace/defense applications, including participation in government R&D programs.

Company size
51-200
Company stage
Debt Financing
Total funding
$92.6M
Headquarters
Tokyo, Japan
Founded
2019

Recently Posted Jobs

Explore more opportunities at EdgeCortix

See more jobs