Staff Machine Learning Engineer - LLM Quantization & Deployment at XPENG

Department: AI Infrastructure Team

Compensation

$215,280 – $364,320/yr

Setup: Hybrid
Location: Santa Clara, California
Type: Full-time
Level: not_specified
Posted: Aug 13, 2026

Description

XPENG is seeking a Lead Research Engineer specializing in Large Language Model (LLM) Deployment and Quality Sign-off. The role involves developing and optimizing VLA inference models, ensuring numerical consistency, and producing high-quality Python code for production environments. The engineer will collaborate with various internal teams to enhance model performance, curate evaluation datasets, analyze numerical errors, and contribute to advancements in autonomous driving.

Required Skills

Transformer Architectures
LLM Inference
PyTorch
Python Programming

Additional Information

Minimum Education: Master's Degree in Computer Science/Electrical Engineering, or equivalent.
Required Previous Experiences: 3-5 years of industry experience.
Strong understanding of Transformer architectures and LLM inference.
Hands-on experience quantizing or deploying deep learning models in production.
Preferred Qualifications: Experience with weight-only, activation, KV-cache, dynamic, static, or mixed-precision quantization.
Experience with AWQ, GPTQ, SmoothQuant, or related methods.
Strong numerical analysis and systems engineering skills.
Experience with one or more LLM runtimes, such as TensorRT-LLM, vLLM, SGLang, llama.cpp, ONNX Runtime, TVM, MLIR, or custom runtimes.
Experience deploying LLMs on resource-constrained or heterogeneous hardware.
Contributions to model optimization, inference, compiler, or serving projects.
Publications at NeurIPS, ICML, ICLR, ACL, or related conferences.
Translation Company Name: XPENG

About XPENG

XPENG

Smart Electric VehiclesGuangzhou, China

XPENG's electric vehicles designed for performance, safety, and sustainability. Explore our range of smart EVs, advanced technology, and commitment to a greener future.

View full company profile