Senior CUDA Kernel & Inference Engineer for AV AI

General Motors; Warren (MI); Hybrid; USD 170,000 - 258,000; Full time

Benefits offered by this job

Hybrid work model

Health and wellbeing benefits

Job summary

General Motors is seeking a talented engineer for the AI Kernels & Compilers team to design and optimize CUDA-based GPU kernels for on-vehicle ML inference in ADAS and autonomous driving. You will push performance, reliability, and scalability within production-grade software across real vehicles.

The role blends kernel development with collaboration across compiler, performance tooling, and architecture teams, requiring strong C++ engineering, CUDA expertise, and system-level thinking.

Qualifications

• Minimum 2+ years of relevant industry experience or equivalent experience.
• BS, MS or PhD in CS, or related technical field.
• Excellent GPU programming skills in CUDA with understanding of parallel programming patterns.
• Hands-on experience benchmarking, profiling, debugging and optimizing accelerator libraries and kernels.
• Strong background in software architecture, library design, and design patterns.

Responsibilities

• Design, implement, benchmark, and iterate on CUDA-based kernels and custom operators to squeeze performance for on-vehicle inference workloads.
• Build and improve tooling and infrastructure to profile, debug, and validate CUDA kernels and accelerator-backend code across the AV stack.
• Partner with AI Solutions, Compilers, and Architecture to translate model and system requirements into kernel roadmaps and plans.
• Collaborate with cross-functional teams to deliver reusable, reliable, high-performance libraries into production.
• Maintain high technology standards and guidelines for GPU kernel development through code review.
• Manage relationships with internal customers to ensure kernels meet real-world needs.

Skills

CUDA programming

C++

GPU programming

NSight tools

Software architecture

Team collaboration

Education

BS, MS or PhD in CS or related field

Tools

CUTLASS

CuTe

Tensor cores

Job description

General Motors is seeking a talented engineer for the AI Kernels & Compilers team to design and optimize CUDA-based GPU kernels for on-vehicle ML inference in ADAS and autonomous driving. You will push performance, reliability, and scalability within production-grade software across real vehicles.

The role blends kernel development with collaboration across compiler, performance tooling, and architecture teams, requiring strong C++ engineering, CUDA expertise, and system-level thinking.