About the Company

XPENG is a leading smart technology company advancing intelligent mobility by integrating AI, machine learning, and autonomous driving into electric vehicles (EVs), eVTOL aircraft, and robotics. With a strong R&D focus, XPENG is transforming the future of transportation through cutting-edge innovation in large-scale AI models, computer vision, and smart connectivity.

About the Role

The Senior Computer Vision Engineer will lead efforts in developing and deploying high-performance AI models optimized for real-world autonomous systems. This role involves applying state-of-the-art compression techniques, optimizing inference on GPUs and custom AI accelerators, and contributing directly to on-vehicle deployment. By pushing the limits of efficient model performance, this position plays a key role in enabling next-generation intelligent systems across XPENG’s product lines.

Key Responsibilities

Optimize large-scale multimodal models for low-latency inference and efficient memory usage.
Apply compression techniques including quantization (INT8/FP16), pruning, and knowledge distillation.
Develop custom inference kernels for GPU and AI accelerator hardware.
Build profiling tools and performance models to identify and resolve bottlenecks.
Contribute to real-world deployment in autonomous driving systems, including testing and iteration.
Stay current with research in efficient ML inference and integrate advancements into production systems.

Minimum Requirements

Master’s or Ph.D. in Computer Science, Electrical Engineering, or related field.
Proficiency in C++ and Python, with a focus on scalable and high-performance software.
Hands-on experience with TensorRT, ONNX Runtime, or TVM for deploying deep learning models.
Familiarity with CUDA programming and parallel computing.
Solid understanding of inference workflows and performance optimization.
Experience in quantization-aware training or post-training quantization.
Strong communication and teamwork skills.

Preferred Qualifications

Experience deploying vision-language or multimodal AI models.
Knowledge of low-precision inference, operator-level optimization, and kernel fusion.
Background in autonomous driving, robotics, or edge AI systems.
Publications or open-source contributions in ML/AI (e.g., NeurIPS, ICML, CVPR).
Expertise in profiling, latency modeling, or compiler-level optimization.

Compensation and Benefits

Base salary: $174,720 – $295,680 (dependent on skills, experience, and location).
Bonus, equity, and comprehensive benefits package.
Access to infrastructure and advanced computational resources.
Supportive and collaborative work culture with opportunities to make a significant impact on the future of mobility.
Perks including meals, snacks, and company activities.

Complete details about this role can be found on the official website below:

Apply Now