Senior Machine Learning Accelerator Engineer - GPU Performance SpecialistGeneral Motors • United States
Dieses Stellenangebot ist nicht mehr verfügbar
Senior Machine Learning Accelerator Engineer - GPU Performance Specialist
General Motors
- United States
- United States
Über
AI Kernels
team specializes in creating high-performance GPU kernels and custom libraries that are pivotal for machine learning inference in Advanced Driver Assistance Systems (ADAS) and autonomous driving. Our objective is to accelerate core AI workloads while ensuring their reliability and maintainability within complex, real-world automotive conditions. Your Responsibilities Include: Designing and developing CUDA-based kernels and custom operators to optimize performance for on-vehicle inference workloads.
Enhancing tools and infrastructure to streamline profiling, debugging, and validation of CUDA kernels and accelerator code within the AV software ecosystem.
Collaborating with AI Solutions, Compilers, and Architecture teams to align kernel development with model and system requirements.
Working cross-functionally to create reliable, reusable, and high-performance libraries ready for production.
Maintaining high standards for GPU kernel development and performance engineering through proactive code reviews.
Building strong relationships with internal stakeholders to ensure that our kernels and libraries fulfill real-world operational needs.
Your Skills & Abilities (Required Qualifications): A minimum of 3 years of relevant industry experience or equivalent.
Bachelor's, Master's, or PhD in Computer Science or a related technical field.
Advanced proficiency in GPU programming with CUDA, along with a solid grasp of parallel programming techniques and GPU architecture.
Hands-on experience in benchmarking, profiling, debugging, and optimizing accelerator libraries to achieve top performance using relevant tools.
Strong background in software architecture, library design, and design patterns.
Proficient in C++ programming and adept at navigating large codebases.
Well-versed in system performance, high-performance computing, and optimization strategies that consider architecture.
Possess strong communication skills and a collaborative mindset to work effectively in a team environment.
Excellent analytical and problem-solving abilities.
Preferred Qualifications (Competitive Advantages): Familiarity with tensor core programming, CUTLASS, or similar libraries.
Knowledge of machine learning model architectures, particularly transformer models.
Experience with low-latency or real-time systems.
Understanding of lower levels of the accelerator software stack, including drivers, runtimes, and compilers.
Compensation:
The salary range for this role is between $128,700 and $261,300. Actual base salary will be determined based on various factors. Bonus Potential:
Opportunities for incentive pay based on company performance and individual contributions.
Benefits:
GM offers a wide range of health and well-being benefits, including medical, dental, vision coverage, retirement plans, vacation time, tuition assistance, and employee discounts.
About GM We are committed to driving change towards a world with Zero Crashes, Zero Emissions, and Zero Congestion, while promoting a responsible and equitable future for all. Why Join Us? At GM, we strive to make impactful choices each day that bring meaningful change and foster a culture where every employee feels connected to our collective mission. Accommodations We welcome all job seekers, including individuals with disabilities. If you require assistance during your job search or application process, please let us know the specific accommodation you need.
Sprachkenntnisse
- English
Hinweis für Nutzer
Dieses Stellenangebot wurde von einem unserer Partner veröffentlicht. Sie können das Originalangebot einsehen hier.