Deep Learning Performance Architect

The Intelligence Accelerator team is responsible for fast and efficient execution of deep learning inference, computer vision, and other compute intensive workloads on next generation autonomous vehicles. You’ll be solving difficult problems that have immediate and valuable real-world applications:

In this role you will: 
  • Design, develop, and ship high-performance software on-vehicle including the execution platform for inference, vision and other sensor processing modules
  • Implement systems for low latency deep-learning based computations on modern SoC, GPU or FPGA compute platforms
  • Ensure correctness, performance and reliability of the system 
  • Influence the product roadmap, and take ownership and responsibility over new projects to make them happen 

Experience with the following is highly valuable: 
  • 3+ years of software experience in Unix/Linux, preferably in a high performance environment
  • Solid C and/or C++ expertise for performance sensitive parallel code
  • Experience with accelerator programming models such as CUDA or OpenCL
  • Prior hands-on experience using GPU, FPGA or other  accelerators to offload computational workloads
  • Understanding of high-performance in-memory data structures, ownership transfer mechanisms and RDMA offloading

Want to apply later?

Type your email address below to receive a reminder

ErrorRequired field

Apply to Job

ErrorRequired field
ErrorRequired field
ErrorRequired field
Error
Error
insert_drive_file
insert_drive_file