Staff Software Engineer – Reliability & Compute Architecture

Neura Market; Mountain View (CA); Hybrid; USD 251,000 - 310,000; Full time

Job summary

Waymo is seeking a Planner/Perception Reliability Engineer to design instrumentation and onboard architectures that proactively prevent reliability issues across computed platforms. You will lead cross-functional initiatives addressing compilers, optimizations, and model changes to improve stability and performance.

The role requires BS/MS in a technical field and hands-on experience with C++, CUDA/GPU acceleration, and GPU kernel development.

Qualifications

• BS/MS in Comp Sci, EE, Robotics, Physics, Math, or equivalent experience.
• Experience in C++.
• Experience with CUDA/GPU/TPU acceleration and model reliability or optimization.
• Experience with writing GPU kernels and evaluation/debugging of GPU workloads.

Responsibilities

• Drive design and development of instrumentation and onboard architecture to prevent, detect, and debug reliability issues across Waymo compute platforms.
• Design and implement long-term strategies to mitigate compute hardware reliability and numerical stability issues across heterogeneous platforms.
• Lead cross-functional initiatives to architect proactive solutions that prevent issues from compilers, optimization, or model changes.
• Architect frameworks and diagnostics to identify and eliminate complex software and firmware faults (deadlocks, memory corruption, race conditions, memory leaks, tail latency).
• Influence design and tooling of next-gen hardware platforms as a technical authority for reliability architecture.

Skills

C++

CUDA/GPU/TPU acceleration

GPU kernels

Model reliability

Education

BS/MS in Computer Science, Electrical Engineering, Robotics, Physics, Math

Job description

Waymo is seeking a Planner/Perception Reliability Engineer to design instrumentation and onboard architectures that proactively prevent reliability issues across computed platforms. You will lead cross-functional initiatives addressing compilers, optimizations, and model changes to improve stability and performance.

The role requires BS/MS in a technical field and hands-on experience with C++, CUDA/GPU acceleration, and GPU kernel development.