Tesla is looking to ensure the quality of its AI hardware and software for current and next-generation platforms, aiming to deploy autonomy at scale in vehicles, robots, and more. This role will contribute to the hardware system that enables advanced AI for vision and planning, supported by efficient inference hardware.
Requirements
- Good understanding of GPU architecture and AI accelerators
- Proficiency in computer architecture
- Proficiency in at least one programming language such as C, C++, Python
- Experience with writing performance tests and analyzing results
- Experience with debugging performance bottlenecks and issues
- Experience with architectural simulators is a plus
- Ability to root cause performance issues and debug esoteric symptoms
Responsibilities
- Analyzing and deploying state-of-the-art neural networks on GPU, AI accelerator and performance models
- Debug performance bottlenecks and issues in hardware or simulation
- Conduct pre- and post-silicon performance analysis to correlate models with real-world hardware behavior
- Propose new hardware features, backed by performance estimates
- Create benchmarking frameworks to assess performance, power, and latency of ML workloads
- Document and communicate findings to cross-functional teams to guide future hardware roadmaps
- Develop performance models and simulation tools to evaluate hardware architectures for machine learning workloads
Other
- Degree in Computer Science, Computer Engineering or Electrical Engineering or equivalent experience
- Previous internship and/or project experience is a plus
- Professional and positive communication skills
