Staff ML Engineer - AI Foundation for Fast Inference

Xpengmotors; Santa Clara (CA); On-site; USD 215,280 - 364,320; Full time

Benefits offered by this job

Competitive compensation package

Snacks, lunches, dinners, and fun activities

Infrastructures and computational resources

Job summary

Xpengmotors is seeking a full-time Machine Learning Engineer to join their team in Santa Clara, California. In this role, you will work on optimizing advanced transformer models for autonomous driving technology, collaborating with a talented group of engineers and researchers.

The ideal candidate holds a Master's degree and has 5-8 years of relevant industry experience, particularly in using PyTorch and designing ML infrastructures. The position offers a competitive salary and opportunities in a supportive environment focused on innovative transport solutions.

Qualifications

• 5-8 years of industry experience in machine learning.
• Deep understanding of memory bandwidth and compute bottlenecks.
• Familiarity with GPU, CPU, NPU, DSP architecture.

Responsibilities

• Optimize transformer-based LLMs for low-latency inference.
• Deploy optimized models across various platforms.
• Contribute to internal tooling for model optimization.

Skills

Knowledge of PyTorch

Programming skills in Python

Programming skills in C++

Knowledge of transformer architecture

Education

Master in CS/CE/EE or equivalent

Tools

CUDA

Triton

Torchscript

Job description

Xpengmotors is seeking a full-time Machine Learning Engineer to join their team in Santa Clara, California. In this role, you will work on optimizing advanced transformer models for autonomous driving technology, collaborating with a talented group of engineers and researchers.

The ideal candidate holds a Master's degree and has 5-8 years of relevant industry experience, particularly in using PyTorch and designing ML infrastructures. The position offers a competitive salary and opportunities in a supportive environment focused on innovative transport solutions.