MemryX Inc is a USA-based startup company specializing in AI accelerator design, with office in Taipei. MemryX is backed by prominent investors and industry leaders, and offers a great career opportunity for both young and experienced engineers.

Once JECHO receives your application, we will help refer your profile to the vacancy. For any other job requests, please visit us on JECHO.ME, or contact our JECHO Consultants.
Upload your CV/resume or any other relevant file. Max. file size: 40 MB.

Who You Are

  • You are an open and honest communicator who values your team
  • You are innovative, enjoy bringing new ideas to the table and are receptive to ideas and feedback from others
  • You’re passionate about advancing the state of the world through new technology
  • You enjoy the ambiguity and pace of a startup environment

What you will be doing

  • Meet with customers and internal team members to plan and execute on development supporting our customers’ requirements and delivery dates
  • Analyze and optimize model structure, operators and provide suggestion to ensure high-performance solutions
  • Integrate the latest accelerator hardware and software with customer applications to validate the MemryX value proposition for each application
  • Contribute to software engineering best practices for development, testing, documentation, and technical reviews
  • Design, create, and execute test plans, test cases, and test scripts for SDKs and DevHub features across multiple platforms/OS

What we expect to see

  • Knowledge of embedded hardware platforms and ensure AI chip compatibility on various embedded hardware
  • Proven ability to translate customer requirements into technical solutions and optimize AI systems accordingly
  • Knowledge of fundamental AI/neural-networks concepts and tools (Object Identification, Object Detection, ONNX, Tensorflow, Pytorch, model operators, compilers, etc)
  • Proven hands-on experience with edge ai deployment frameworks such as OpenVINO or TensorRT
  • Strong problem-solving skills and an ability to troubleshoot and debug complex multi-dimensional problems
  • Work closely with AI engineers to understand and translate requirements into practical AI solutions
  • Practical knowledge of agile development using tools such as Jira, Git and GitHub

What we’re happy to see

  • Proficiency in AI application development using Python/C/C++, with experience in ML libraries (ONNX, PyTorch and TensorFlow)
  • Direct experience in embedded computer vision systems (Camera system integration and optimization, OpenCV, Gstreamer, etc)

Requirements

  • BS/MS in Computer Science with 3+ years of experience in AE, SW, Systems
  • Hands-on experience in AI (specifically Deep Neural Networks) and AI frameworks (TensorFlow, Keras, PyTorch, ONNX), Computer Vision, NN models
  • Experience in Linux, Windows, embedded platform OS
  • Self-driven with the ability to work in a startup

Tagged as: AI, ML, onnx, pytorch, Tensorflow

Leave a Reply or a Review

*