Senior Machine Learning Compiler Engineer

General Motors

United States

United States

Apply Now

About

Job Description About the Mission Join us in revolutionizing the future of mobility with GM's vision of Zero Crashes, Zero Emissions, and Zero Congestion. The Autonomous Vehicle (AV) organization is at the forefront of developing advanced automated driving technologies, including Level 4-capable fully self-driving systems, to enhance safety, sustainability, and accessibility in transportation. As part of the AI Kernels & Compilers team, your work will directly impact how vehicles perceive, predict, and plan for their environment by transforming cutting-edge research into reliable, production-grade software that operates efficiently on real vehicles. You will play a pivotal role in ensuring that every processing cycle contributes to improved situational awareness and rapid response times on the road. About the Team The AI Compiler team is essential in enabling advanced AI models to function seamlessly within vehicles. We develop the compiler that converts high-level models into efficient inference across GPUs, driving GM's next-generation autonomous and assisted driving features. Your work will involve optimizing graph lowering, enhancing operator coverage, improving kernel integration, and refining deployment tooling to maximize performance, correctness, and robustness in real-world conditions. In close collaboration with AI Deployments, AI Solutions, Runtime, and AI Kernels teams, you will drive the creation of a platform that expedites the transition of research innovations to fleet-ready solutions. Join our team of experts in compiler technology, systems engineering, and GPU architecture who tackle complex challenges, explore the internals of MLIR/ONNX and CUDA/TensorRT, and mentor colleagues in performance engineering. We value precise thinking, strong engineering principles, and foster a culture where everyone's contributions help shape the future of autonomous driving. The Role As a Senior Compiler Engineer on the AI Kernels & Compilers team, you will oversee the entire compilation process that transforms high-level models into highly optimized inference artifacts for GM's autonomous and assisted driving platforms. You will set the technical vision and develop tools that streamline the compilation process for ML engineers across the AV organization. Your responsibilities will include designing and enhancing the model export and compilation pipeline—from capturing high-level model graphs through to intermediate representations and compiler transformations—ultimately delivering accelerator-specific inference engines and their integration with our runtime. Your goal will be to optimize compilation throughput, maintain model fidelity, and minimize latency on vehicles, while also building robust tools for validating numerical correctness, identifying performance regressions, and providing actionable diagnostics to model authors. If you're excited about working at the intersection of
compilers, performance engineering, and real-world autonomy , this role allows you to make impactful decisions that determine what runs in our vehicles. Your Responsibilities Lead and enhance
the model compilation toolchain for deploying large-scale perception, prediction, and planning models to the AV.
Design new compiler passes and analyses
to improve build times, manage memory usage, and reduce runtime latency while adhering to rigorous safety and reliability standards.
Collaborate with kernel, runtime, and hardware teams
to define interfaces, influence accelerator features, and ensure the compiler elucidates the necessary abstractions for optimal performance.
Establish standards and best practices
for model export, validation, and debugging, enabling AV teams to work iteratively with clear performance and accuracy metrics.
Your Skills & Abilities (Required Qualifications) 5+ years of experience in compiler development.
Familiarity with ML frameworks such as PyTorch, TensorFlow, or JAX and related software stacks including ONNX, MLIR, XLA, TVM, TensorRT, etc.
Strong proficiency in developing production-quality software using Python or C++.
Expertise in the software development lifecycle encompassing coding, debugging, optimization, testing, and integration.
Bachelor's degree or higher in Computer Science, Computer Engineering, Electrical Engineering, or a related field.
Preferred Qualifications Experience in building and optimizing ONNX-based model export and deployment pipelines.
Proficiency in GPU programming (CUDA) and familiarity with machine learning software stacks like cuDNN and cuBLAS.
Understanding of ML accelerators and their hardware architecture.
Experience in developing and deploying machine learning models.
Compensation Details The expected salary for this role is between $185,100 and $335,300. Your actual base salary will depend on individual qualifications and experience.
A bonus program is available that rewards individuals based on performance and company results.
Benefits GM provides a competitive range of health and well-being programs, including medical, dental, and vision coverage, as well as retirement savings plans, paid time off, tuition assistance, and vehicle discounts. Please note: Depending on your motor vehicle report evaluation outcome, you may qualify for a company vehicle program, which allows you to drive and assess a General Motors vehicle. The successful candidate will adhere to GM's inclusivity and diversity principles, fostering a workplace environment free from discrimination. We encourage you to apply and become part of a team committed to creating a safer and equitable future for all.

United States

Languages

English

Notice for Users

This job comes from a TieTalent partner platform. Click "Apply Now" to submit your application directly on their site.

Apply Now