Machine Learning Engineer, AI Inference Solutions (University Grad)
Core
Build ML deployment platforms and optimize models for real-time, safety-critical inference on autonomous vehicle hardware.
Role type
Early-career Machine Learning Engineer (AI Inference Solutions)
Builds
ML deployment platform, model-optimization workflows, and inference benchmarking/profiling infrastructure for GM's Super Cruise fleet.
Domain
Autonomous driving / Automotive / Machine Learning Systems
Deliverable
production ML models
Required skills
Python, C++, computer science fundamentals (data structures, algorithms, OS, architecture), AI/ML (deep learning, computer vision), software engineering, model optimization (quantization, pruning, distillation)
Preferred skills
GPU programming (CUDA, Triton), ML compilers (torch.compile, TensorRT, ONNX), distributed systems, Linux development, agentic/LLM tooling
Technologies
PyTorch, CUDA, OpenAI Triton, TensorRT, ONNX, vLLM, Nsight Systems, Nsight Compute, Airflow, Temporal, Flyte, Ray, Kubeflow
Responsibilities
Contribute production code for deployment platforms and optimization workflows; pair with seniors on performance investigations and model-optimization experiments; build and maintain platform tools (validators, probes, analyzers); root-cause production deployment or performance issues; collaborate with cross-functional teams (kernels, compiler, parity) on model deployments; participate in code reviews and technical documentation.
Seniority
Early-career / New Graduate (via careerplan.io/jobs/JR-202610103-machine-learning-engineer-ai-inference-solutions-university-grad-at-generalmotors)
