Senior ML Engineer: LLM Inference & Quantization

XPENG; Santa Clara (CA); On-site; USD 175,000 - 296,000; Full time

Benefits offered by this job

Competitive compensation

Snacks and meals

Cutting-edge technologies

Top talents collaboration

Job summary

XPENG, a leading smart technology company, seeks a qualified engineer to advance VLA inference and model quantization for next-gen XPENG Turing AI chip. You will develop production-grade Python code, build end-to-end pipelines, and work with research, systems, and in-vehicle teams.

The role focuses on PTQ and QAT workflows, performance benchmarking, and validating models in real-world simulations. Strong PyTorch experience, quantization know-how, and collaboration skills are essential for

Qualifications

• Master in CS/CE/EE, or equivalent, with 1-3 years of industry experience.
• Strong understanding of Transformer architectures and LLM inference.
• Hands-on experience 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.
• Ability to work effectively across research, systems, infrastructure, and product teams.
• Excellent communication and problem-solving skills, with the ability to thrive in a fast-paced and collaborative environment.

Responsibilities

• Develop VLA inference models, ensure numerical consistency with training models, and productionize LLM quantization methods.
• Develop production-quality Python code with strong testing, observability, reproducibility, and failure handling.
• Build robust model export, calibration, benchmarking, validation, and deployment pipelines.
• Engage early with the VLA model research team to establish performance estimates and prove model feasibility.
• Curate evaluation datasets and establish a comprehensive metric suite to benchmark performance.
• Analyze numerical errors, accuracy regressions, and performance trade-offs.
• Develop PTQ and QAT orchestration workflows.
• Serve as the primary interface with field-testing and simulation teams for issue triage and autonomous driving performance sign-off.
• Collaborate with the in-vehicle software team on latency analysis and issue triage.
• Collaborate with the training infrastructure team to develop QAT and model distillation.

Skills

Transformer architectures

LLM inference

Python programming

PyTorch

Software engineering

Communication

Cross-functional collaboration

Education

Master's degree in CS/CE/EE

Tools

TensorRT-LLM

vLLM

llama.cpp

ONNX Runtime

Job description

XPENG, a leading smart technology company, seeks a qualified engineer to advance VLA inference and model quantization for next-gen XPENG Turing AI chip. You will develop production-grade Python code, build end-to-end pipelines, and work with research, systems, and in-vehicle teams.

The role focuses on PTQ and QAT workflows, performance benchmarking, and validating models in real-world simulations. Strong PyTorch experience, quantization know-how, and collaboration skills are essential for