Senior ML Compiler Engineer

AbouttheMission

GMs vision of Zero Crashes Zero Emissions and Zero Congestion guides everything we do in autonomous and assisted driving. The AV organization is building advanced automated driving technologiesincluding Level 4capable fully self-drivingsystemstomove us toward safer more sustainable and more accessible mobility.

For theAIKernels & Compilers team that mission shows up in the details: turning cuttingedgeperception prediction and planning research into productiongrade software that can run efficiently and reliably on real vehicles at scale. We pioneernew approachesto model exportkernel development and performance engineering so that every cycle on our accelerators translates into better situational awareness faster reaction times and more robust behavior on the road.

If you want your compiler andkernelsworktodirectlyinfluencehow automated vehicles understand and react to the world whileoperatingatthesafetyreliabilityand scaleof a company like GM this is where that impact becomes real.

About the Team

The AI Compiler team sits at the heart of how advanced AI models make it onto the car. We own the compiler that turns highlevel models into fast reliable inference across GPUs powering GMs nextgeneration autonomous and assisted driving features.

Our work spans graph lowering operator coverage kernel integration and deployment tooling with a mandate to squeeze every millisecond out of onvehicle workloads while preserving correctness and robustness in realworld conditions. We partner closely withAI DeploymentsAI Solutions Runtime andAI Kernelsteams to codesignaplatform thatenablesnew ideasin researchto bequickly and safelyshippedto production fleets.

Youlljoin a group ofdeepcompiler systems and GPU engineerswho enjoyworking onhard problemsanddiving into MLIR/ONNXand CUDA/TensorRTinternals. We value clear thinking strong engineering fundamentals and a culture where people can do the best work of their careers on problems that directly shape the future of automated driving.

The Role

As aSeniorCompiler Engineer on the AI Kernels & Compilers team you willwork on thecompilation stack that takes highlevel models and turns them into highly optimized inference artifacts running on GMs autonomous and assisted driving platforms.Youllbe a key contributor to a pipeline andtooling that makesthat path fast reliable andeffortlessfor ML engineers across the AV organizationto compile their models.

You willwork on an evolvinga state-of-the-artmodel export and compilation pipelinefrom capturing highlevel model graphs through intermediate representations and compiler transforms into acceleratorspecific inference engines and their integration with our runtimeso that we can simultaneouslyoptimizecompilation throughput model fidelity and onvehicle latency. Along the wayyoullbuild robust tooling tovalidatenumerical correctnessdetectand bisect performance regressions and surface clear actionable diagnostics back to model authors.

If you want to work at the intersection ofcompilers performance engineering and realworld autonomy this role puts your decisions directly on the critical path of what runs on the car.

Whatyoullbe doing (Responsibilities)