Machine Learning Engineer, AI Inference Solutions (University Grad)

About this role

Job Description General Motors is a global leader in advanced driver   assistance , with Super Cruise hands-free technology in more than 500,000 equipped vehicles on the road and over 700 million hands-free miles driven— demonstrating   that automation can be trusted, intuitive, and helpful while reaching everyday drivers at unprecedented scale. Within GM AV, the Model Deployment & Inference Solutions team deploys machine learning models from training frameworks (e.g.,   PyTorch ) onto autonomous-vehicle hardware; our two-fold mission is to build the ML deployment platform that makes model rollouts fast and predictable, and to optimize models so they meet the real-time latency and memory budgets required to run on-vehicle. Our work sits on the critical path for GM’s publicly committed launch of eyes-off (hands-free, eyes-free) autonomous driving in 2028 on the Cadillac Escalade IQ, and   we’re   hiring engineers to help deliver the next generation of safe, delightful personal autonomous-vehicle experiences.  

About the R o le   

As an early career Engineer on the Model Deployment & Inference Solutions team,   you’ll   contribute across both sides of our mission: building the ML deployment platform and   optimizing   models for on-vehicle inference.   You’ll   work with and learn from senior engineers on real production deployments, platform features, and model-optimization workflows that ship to GM’s Super Cruise fleet at large scale, with structured mentorship and a clear onboarding plan.   You’ll   also collaborate closely with our sister teams (kernels,   compiler , reduced precision, and parity) on the end-to-end path that takes trained models from research frameworks to ultra-efficient, safety-critical inference on the car.   This is an   early-career   / new graduate role designed for candidates who have recently or will be completing their degree by June 2026.   

What   You’ll   Do (Responsibilities)  

• Contribute production code across the     ML deployment platform ,   model-optimization workflows , and   inference   benchmarking/profiling infrastructure.   

• Pair with senior engineers on   deployment workflows ,   performance investigations ,   model-optimization experiments   (e.g., quantization, pruning, distillation), and   platform tooling .  

• Build, test, and   maintain   platform tools (e.g., validators, performance probes, parity and sensitivity analyzers, agentic specialists) with technical guidance and code review support.  

• Investigate and help root-cause production deployment or performance issues; learn and apply the diagnostic playbook for   compiler ,   kernel , runtime, and parity bugs.  

• Collaborate with cross-functional teams across the AV organization ;   including kernels, compiler, reduced-precision, parity, and model-development groups—to plan and execute model deployments to the AV stack, working under the guidance of senior engineers  

• Participate in code reviews, design discussions, and technical documentation to ensure reliability, correctness, and clear abstractions in a large-scale codebase.  

• Learn and follow secure coding, safety, and compliance practices   required   for on-vehicle autonomous driving software.  

Your Skills & Abilities ( Required Qualifications )  

• Recently completed or   completing   a   Bachelor’s or   Master’s   degree by   Spring 2026 in   Computer Science ,   ECE , or a rela ted   t echnica l field . (Degree must be   completed before your start date. )  

• Strong   computer science fundamentals   (e.g., data structures, algorithms, operating systems, computer architecture) and solid coding skills in   Python   and/or   C++ ,   demonstrated   through coursework, internships, or substantial projects.  

• Hands-on experience in   AI/ML   (e.g., machine learning, deep learning, computer vision, NLP, or ML systems) via classes, research, internships, or personal projects.  

• Depth in at least one of:   computer architecture ,   operating systems ,   distributed systems , or   compilers .  

• Demonstrated software-engineering experience (internships, coursework, open-source, research code, or competitions) showing good judgment around   r eliability, correctness, and clean abstractions .  

• Experience with—or strong interest in—using   coding assistants/agents   (e.g., Cursor, Claude Code, GitHub Copilot) as part of your workflow.  

• Ability to work effectively in collaborative, cross-functional teams and communicate clearly—both in writing and verbally—including explaining technical work   partners  

What Will Give You a Competitive Edge (Preferred Qualifications)  

• Internship, research, or advanced coursework in   ML systems ,   ML compilers ,   GPU programming   (CUD A, OpenAI Triton),   inference optimization , or   distributed training/serving infrastructure .  

• Familiarity with   PyTorch   and modern ML compiler/runtime stacks (e.g.,   torch.compile ,   TensorRT , ONNX, Triton Inference Server,   vLLM , or equivalent).  

• Exposure to   model optimization   (quantization, pruning, distillation) or   GPU profiling tools   (Nsight Systems, Nsight Compute,   PyTorch   Profiler).  

• Familiarity with workflow/ML platforms such as   Airflow, Temporal, Flyte, Ray, or Kubeflow .  

• Experience building   agentic or LLM-powered tools or workflows .  

• Open-source contributions related to   PyTorch,   TensorRT ,   vLLM, OpenAI Triton , or similar projects.  

• Coursework, projects, or publications touching   ML systems   (e.g.,   MLSys , OSDI, ASPLOS, HPCA,   NeurIPS   systems track).  

• Familiarity with a systems language (e.g.,   C++ ) and development in a   Linux   environment.  

Location  

• Sunnyvale, CA  

• This role is categorized as   hybrid . This means the selected candidate is expected to report to a specific location at least 3 times a week.   

• This job may be eligible for relocation benefits  

Compensatio n  

The compensation information is a good faith estim

Similar jobs

• Machine Learning Engineer - Inference — Togetherai · San Francisco
• Software Engineer, Inference AI/ML — Coreweave · Sunnyvale, CA / Bellevue, WA
• Applied AI Engineer, Inference — Coreweave · Bellevue, WA/ San Francisco, CA/ Sunnyvale, CA
• Machine Learning Engineer, AI Labs — Netskope · Santa Clara, California, United States
• Machine Learning Infrastructure Engineer, Model Inference — Abridge · Remote
• Tech Lead - AI Inference — Wekatest · Remote
• Senior Deep Learning Software Engineer, Inference — NVIDIA · Remote
• Graduate AI Engineer — Allica-bank · Remote