[Japan] Compiler Software Engineer

The Team

As a team, we are working to define and solve the hardest problems in AI including computer vision, speech, and natural language, geared towards real-time capabilities on small to medium-form factor devices. We originated out of multiple years of research, as such at our core we value learning, intellectual curiosity, and self-starters. We have the ambitious goal of enabling cloud-level performance with significantly better energy efficiency for AI inference at the edge. Your Role and Responsibilities

In this role, working closely with our hardware and ML engineers, you will extend our compiler and software toolchain for deploying machine learning models with high performance and flexibility on our proprietary AI hardware accelerator. Minimum Qualifications

• Bachelor's in Computer Engineering, Computer Science and/or Electrical Engineering. - 5+ years of Software Engineering experience. - 3+ years experience in writing production-quality C++. - 2+ years experience developing Python, including pip packaging and C++ bindings. - 2+ years of experience on ML graph optimization passes

• 1+ years experience using the MLIR/LLVM framework. - Experience with code management using Git and familiarity with GitHub/GitLab PR flow. - Exposure to CI/CD tools such as Jenkins. - Knowledge of ML quantization techniques and mixed precision inference. - Strong debugging and analysis skills, for root causing complex issues. Preferred Qualifications

• Knowledge of neural networks, with hands-on experience using ML frameworks such as TensorFlow/PyTorch/ONNX. - Knowledge of Convolutional Neural Networks (CNNs), RNN/LSTMs or Transformers (LLMs) and familiarity with multi-modal ML models. - Experience developing embedded software, preferably for ASIC or on-device ML. - Experience with low level machine specific code generation (e.g. x86, RISC-V or similar)