ML Deployment Engineer for On-Vehicle Inference

General Motors LLC; Sunnyvale (CA); Hybrid; USD 119,000 - 151,000; Full time

Benefits offered by this job

Health benefits

Retirement plan

Tuition assistance

Employee assistance program

GM vehicle discounts

Paid vacation

Job summary

General Motors in Sunnyvale, CA is seeking an early-career Engineer for the Model Deployment & Inference Solutions team to build an ML deployment platform and optimize models for on-vehicle inference.

You will work with senior engineers on real deployments, tooling, and end-to-end ML workflows, with mentorship and onboarding. This role targets new graduates by Aug 2026 and offers growth opportunities.

Qualifications

• Bachelor’s or Master’s in CS, ECE, or related field, completed by start date.
• Strong CS fundamentals and Python/C++ coding skills.
• Hands-on AI/ML experience via coursework or projects.
• Experience with reliable, clean software engineering practices.
• Interest in using coding assistants in workflow.

Responsibilities

• Contribute production code across ML deployment platform and model-optimization workflows.
• Pair with senior engineers on deployment workflows and performance investigations.
• Build, test, and maintain platform tools with guidance and reviews.
• Investigate and help root-cause deployment or performance issues.
• Collaborate with cross-functional teams to plan model deployments to the AV stack.
• Participate in code reviews, design discussions, and documentation.
• Follow secure coding and safety practices for on-vehicle software.

Skills

Python

C++

AI/ML

Algorithms

Data structures

Operating systems

Computer architecture

Distributed systems

Compilers

Team collaboration

Communication

Coding assistants

Education

Bachelor’s or Master’s degree

Tools

PyTorch

TensorRT

Torch.compile

ONNX

Triton

vLLM

CUDA

Nsight

Airflow

Kubeflow

Job description

General Motors in Sunnyvale, CA is seeking an early-career Engineer for the Model Deployment & Inference Solutions team to build an ML deployment platform and optimize models for on-vehicle inference.

You will work with senior engineers on real deployments, tooling, and end-to-end ML workflows, with mentorship and onboarding. This role targets new graduates by Aug 2026 and offers growth opportunities.