Senior Computer Vision and Deep Learning Hardware Architect

at NVIDIA · Industrial · Shanghai, China

NVIDIA is seeking an Autonomous Vehicle Performance Architecture Engineer to design, model, and verify state-of-the-art programmable vision accelerators (PVA) for automotive and robotics. The role involves optimizing software for autonomous driving solutions, analyzing and prototyping applications, building performance models for future architectures, and collaborating with teams to enhance PVA architecture. Requires a Masters/PhD, 3+ years of relevant experience, strong C/C++ and computer architecture skills, and performance modeling/optimization expertise. Experience in DSP programming, autonomous vehicle software, deep learning, computer vision, and self-driving cars is a plus.

What you'd actually do

  1. Work on delivering most efficient software on PVA for Autonomous Driving solutions
  2. Analyze, prototype and optimize key applications for both existing and new architectures for PVA
  3. Build model to predict performance, power and reliability on future architectures and propose and evaluate new architecture features
  4. Be involved in crafting tools to analyze, simulate, validate and verify application performance and energy consumption
  5. Collaborate with different teams to improve the PVA architecture to extend the state of the art in performance, efficiency, reliability and programmability

Skills

Required

  • Masters or PhD (or equivalent experience)
  • 3+ years of experience equivalent experience in relevant discipline (CE, CS&E, CS, AI)
  • Excellent C/C++ programming and software design skills
  • Strong background in computer architecture, high performance computing
  • Performance modelling, profiling, debug, and code optimization or architectural knowledge of CPU and DSP

Nice to have

  • DSP programming, performance analysis, modelling and optimization experience
  • GPU programming experience is a plus
  • Autonomous vehicle software development experience
  • Expertise in characterizing and modeling system-level performance, executing comparison studies, and documenting and publishing results
  • Experience in deep learning, computer vision and self-driving car domain

What the JD emphasized

  • Autonomous Vehicle Performance Architecture Engineer
  • programmable vision accelerator (PVA)
  • computer vision applications and kernels
  • Autonomous Driving solutions
  • architecture modeling, designing and verifying
  • performance, power and reliability on future architectures
  • validate and verify application performance and energy consumption
  • computer architecture
  • high performance computing
  • Performance modelling, profiling, debug, and code optimization
  • architectural knowledge of CPU and DSP
  • DSP programming, performance analysis, modelling and optimization experience
  • deep learning
  • computer vision
  • self-driving car domain

Other signals

  • designing the state-of-art programmable vision accelerator (PVA)
  • delivering most high-performance/efficient computer vision applications and kernels
  • architecture modeling, designing and verifying
Read full job description

We’re looking for an Autonomous Vehicle Performance Architecture Engineer. NVIDIA MMPLEX PVA team is designing the state-of-art programmable vision accelerator (PVA) which targets the automotive and robotic area. We are responsible for the architecture modeling, designing and verifying. We also deliver most high-performance/efficient computer vision applications and kernels to the world-wide customers.

What you'll be doing:

  • Work on delivering most efficient software on PVA for Autonomous Driving solutions
  • Analyze, prototype and optimize key applications for both existing and new architectures for PVA
  • Build model to predict performance, power and reliability on future architectures and propose and evaluate new architecture features
  • Be involved in crafting tools to analyze, simulate, validate and verify application performance and energy consumption
  • Collaborate with different teams to improve the PVA architecture to extend the state of the art in performance, efficiency, reliability and programmability

What we need to see:

  • Masters or PhD (or equivalent experience)
  • 3+ years of experience equivalent experience in relevant discipline (CE, CS&E, CS, AI)
  • Excellent C/C++ programming and software design skills
  • Strong background in computer architecture, high performance computing
  • Performance modelling, profiling, debug, and code optimization or architectural knowledge of CPU and DSP

Ways to stand out from the crowd:

  • DSP programming, performance analysis, modelling and optimization experience (GPU programming experience is a plus)
  • Autonomous vehicle software development experience
  • Expertise in characterizing and modeling system-level performance, executing comparison studies, and documenting and publishing results
  • Experience in deep learning, computer vision and self-driving car domain