- Support model quantization and deployment efforts for large-scale multimodal models, including Transformers and vision-language models.
- Assist with applying model optimization techniques such as post-training quantization, quantization-aware training, pruning, and related compression methods under guidance from senior engineers.
- Work with research and platform teams to help improve model deployability and understand hardware and runtime constraints.
- Contribute to deployment tools, test pipelines, and runtime modules in C++ and Python for autonomous driving systems.
- Help analyze model performance, memory usage, latency, and numerical accuracy across different deployment targets.
- Participate in debugging and performance tuning across the model, runtime, and system stack.
- Support validation and testing workflows to ensure stable and reliable deployment in vehicle and simulation environments.
- BS, MS, or PhD in Computer Science, Electrical Engineering, Robotics, or a related field.
- Strong programming skills in C++ and/or Python.
- Familiarity with deep learning frameworks such as PyTorch.
- Basic understanding of model inference, deployment, or optimization workflows using tools such as ONNX, TensorRT, or similar frameworks.
- Exposure to model compression or quantization concepts such as INT8, FP16, or related approaches.
- Interest in computer architecture, performance optimization, and edge or embedded systems.
- Strong problem-solving skills and the ability to learn quickly in a fast-paced engineering environment.
- Good communication skills and the ability to collaborate with cross-functional teams.
- Internship, research, or project experience in deep learning model deployment, inference acceleration, or embedded AI.
- Familiarity with Transformers, multimodal models, or foundation models.
- Experience with CUDA or GPU programming.
- Exposure to autonomous driving, robotics, or real-time systems.
- Contributions to research projects, open-source repositories, or relevant course projects.
- A fun, supportive and engaging environment.
- Infrastructures and computational resources to support your work.
- Opportunity to work on cutting edge technologies with the top talents in the field.
- Opportunity to make significant impact on the transportation revolution by the means of advancing autonomous driving.
- Competitive compensation package.
- Snacks, lunches, dinners, and fun activities.
What We Do
Xpeng Motors is a leading Chinese electric vehicle and technology company that designs and manufactures intelligent automobiles that are seamlessly integrated with the Internet and utilize the latest advances in artificial intelligence. Focusing on China’s young and tech-savvy consumer base, XPENG Motors strives to offer smart mobility solutions with technology innovation and cutting-edge R&D. The company’s initial backers include its CEO & Chairman He Xiaopeng, the founder of UCWeb Inc. and a former Alibaba executive. It was co-founded in 2014 by Henry Xia and He Tao, former senior executives at Guangzhou Auto with expertise in innovative automotive technology and R&D. It has received funding from prominent Chinese and international investors including Alibaba Group, Foxconn Group and IDG Capital. Currently with 3,000 employees, the company is headquartered in Guangzhou and has design, R&D, manufacturing and sales & marketing divisions in Silicon Valley, San Diego, Beijing, Shanghai, Zhaoqing (Guangdong Province) and Zhengzhou (Henan Province).
