Machine Learning Engineer, AI Inference Solutions (Automotive)

TL;DR

Machine Learning Engineer (AI Inference): Deploying and optimizing ML models for autonomous vehicle hardware with an accent on real-time latency and memory budgets. Focus on building ML deployment platforms, implementing model optimization techniques like quantization and pruning, and ensuring safety-critical inference performance on-vehicle.

Location: Hybrid (Sunnyvale, CA). Must report to the office at least 3 times a week.

Salary: $119,250 – $150,850

Company

Global leader in advanced driver assistance and autonomous vehicle technology, developing the Super Cruise hands-free system.

What you will do

• Develop production code for the ML deployment platform, optimization workflows, and inference profiling infrastructure.
• Perform model-optimization experiments including quantization, pruning, and distillation.
• Build and maintain platform tools such as validators, performance probes, and parity analyzers.
• Root-cause production deployment and performance issues across compilers, kernels, and runtimes.
• Collaborate with cross-functional teams (kernels, compiler, and model-development) to execute AV stack deployments.
• Adhere to secure coding, safety, and compliance practices for on-vehicle autonomous driving software.

Requirements

• Bachelor’s or Master’s degree in Computer Science, ECE, or a related technical field by Spring 2026.
• Strong fundamentals in data structures, algorithms, operating systems, and computer architecture.
• Solid coding skills in Python and/or C++.
• Hands-on experience in AI/ML (deep learning, computer vision, or NLP).
• Depth in at least one of: computer architecture, OS, distributed systems, or compilers.
• Must be based in or be able to relocate to Sunnyvale, CA.

Nice to have

• Experience with GPU programming (CUDA, OpenAI Triton) or ML compilers.
• Familiarity with PyTorch, TensorRT, ONNX, vLLM, or Triton Inference Server.
• Exposure to GPU profiling tools (Nsight Systems, Nsight Compute, PyTorch Profiler).
• Experience with ML platforms like Airflow, Temporal, Flyte, Ray, or Kubeflow.
• Open-source contributions to PyTorch, TensorRT, or similar ML systems projects.

Culture & Benefits

• Hybrid work environment with structured mentorship and a clear onboarding plan for early-career engineers.
• Comprehensive health and wellbeing programs including medical, dental, and vision.
• Financial security with a retirement savings plan, Health Savings Account (HSA), and Flexible Spending Accounts (FSA).
• Paid vacation, holidays, and tuition assistance programs.
• Exclusive GM vehicle discounts.