Senior LLM Inference & Quantization Engineer

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

Benefits offered by this job

Fun and engaging environment

Computational resources provided

Cutting-edge technologies

Impact on autonomous driving

Competitive compensation

Snacks and meals

Job summary

XPENG is seeking a talented engineer to advance VLA inference models and LLM quantization in production. You will implement robust pipelines, curate datasets, and collaborate across research, systems, and vehicle software teams to ensure high-quality sign-off for autonomous driving features.

The role emphasizes Python, PyTorch, and strong software engineering with a focus on reliability, testing, and performance optimization.

Qualifications

• Master in CS/CE/EE, or equivalent.
• 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.

Responsibilities

• Develop VLA inference models and productionize LLM quantization methods.
• Develop production-quality Python code with testing and observability.
• Build model export, calibration, benchmarking, validation, and deployment pipelines.
• Engage with the VLA model research team to establish performance estimates.
• Curate evaluation datasets and establish metric suite for benchmarking.
• Analyze numerical errors, accuracy regressions, and performance trade-offs.
• Develop PTQ and QAT orchestration workflows.
• Interface with field-testing and simulation teams for issue triage and sign-off.
• Collaborate with in-vehicle software and training infra teams.

Skills

Transformer architectures

LLM inference

Python programming

Software engineering

Problem-solving

Education

Master in CS/CE/EE

Tools

PyTorch

Job description

XPENG is seeking a talented engineer to advance VLA inference models and LLM quantization in production. You will implement robust pipelines, curate datasets, and collaborate across research, systems, and vehicle software teams to ensure high-quality sign-off for autonomous driving features.

The role emphasizes Python, PyTorch, and strong software engineering with a focus on reliability, testing, and performance optimization.