Staff LLM Quantization & Deployment Engineer

XPENG; Santa Clara (CA); On-site; USD 215,000 - 364,000; Full time

Benefits offered by this job

Competitive compensation package

Infrastructures and computational资源

Job summary

XPENG in Santa Clara, CA, is seeking a Staff Machine Learning Engineer to advance LLM quantization and on-vehicle deployment. You will develop PTQ, QAT, mixed-precision inference, and robust production pipelines.

The role requires a Master in CS/EE, 3–5 years of experience, strong PyTorch and Python skills, and the ability to collaborate across research, systems, and product teams. We offer competitive compensation and ample resources.

Qualifications

• Master in CS/CE/EE with 3–5 years industry experience.
• Strong understanding of Transformer architectures and LLM inference.
• Hands-on quantizing or deploying deep learning models in production.
• Proficiency with PyTorch and at least one inference or compilation stack.
• Strong Python programming and software engineering skills.

Responsibilities

• Develop VLA inference models and productionize PTQ/QAT and mixed-precision methods.
• Build production-grade Python code with testing, observability, and failover handling.
• Create export, calibration, benchmarking, validation, and deployment pipelines.
• Collaborate with VLA research, in-vehicle software, and training infra teams.
• Analyze performance, latency, and numerical accuracy across systems.

Skills

Transformer models

LLM inference

Python programming

Software engineering

Cross-functional collaboration

Problem solving

Education

Master in CS/CE/EE

Tools

PyTorch

Job description

XPENG in Santa Clara, CA, is seeking a Staff Machine Learning Engineer to advance LLM quantization and on-vehicle deployment. You will develop PTQ, QAT, mixed-precision inference, and robust production pipelines.

The role requires a Master in CS/EE, 3–5 years of experience, strong PyTorch and Python skills, and the ability to collaborate across research, systems, and product teams. We offer competitive compensation and ample resources.