ML Accelerator Architect - High-Performance Autonomy Compute

Waymo LLC; New York (NY); On-site; USD 251,000 - 310,000; Full time

Benefits offered by this job

Bonus program

Equity incentives

Benefits package

Job summary

Waymo LLC is seeking a senior hardware engineer to analyze inference workloads and map them efficiently to CPUs/GPUs/ML accelerators. You will build scalable performance modeling tools and work with compiler and model teams to influence architectural tradeoffs for autonomous-driving models.

The role requires an MS in CS/CE with 10+ years in high-performance architecture design and 3+ years in ML architectures, plus strong programming and problem-solving skills.

Qualifications

• MS in Computer Science or Computer Engineering or equivalent practical experience.
• 10+ years designing/architecting complex high-performance architectures (CPUs/GPUs/ML accelerators).
• 3+ years experience with machine learning architectures, acceleration and model optimization.
• Deep knowledge of ML model architectures and their compute characteristics.

Responsibilities

• Analyze inference workloads and map them to hardware, proposing HW-friendly implementations and projecting performance.
• Build scalable tools for performance modeling and evaluation of inference workloads.
• Collaborate with compiler and model teams to influence engineering tradeoffs and future model architectures.
• Architect, simulate and design novel hardware solutions for state-of-the-art autonomous driving models.
• Interact with cross-functional teams to realize architectural vision.

Skills

Strong programming

Algorithmic problem solving

Education

MS in Computer Science or Computer Engineering

Job description

Waymo LLC is seeking a senior hardware engineer to analyze inference workloads and map them efficiently to CPUs/GPUs/ML accelerators. You will build scalable performance modeling tools and work with compiler and model teams to influence architectural tradeoffs for autonomous-driving models.

The role requires an MS in CS/CE with 10+ years in high-performance architecture design and 3+ years in ML architectures, plus strong programming and problem-solving skills.