9 months ago
Base Salary
$175k - $296k/yr
Responsibilities
- Optimize transformer-based large language models for low-latency and high-throughput inference.
- Optimize kernels and model graphs using CUDA, Triton, and custom fused operators.
- Implement and benchmark quantization, knowledge distillation, structured and unstructured pruning, and KV-cache optimization.
- Deploy optimized models across GPUs, CPUs, and edge accelerators.
- Contribute to internal tooling and documentation for model optimization flows.
- Collaborate with software engineers, machine learning engineers, and research scientists on autonomous driving models.
Requirements
- Master’s degree in computer science, computer engineering, or electrical engineering, or equivalent experience.
- At least 3 years of industry experience.
- Good knowledge of PyTorch.
- Knowledge of transformer architecture and methods for accelerating transformer training and inference.
- Preferred experience in the autonomous driving industry.
- Preferred knowledge of TorchScript and NVIDIA TensorRT.
- Strong programming skills in Python and C++.
- Familiarity with GPU, CPU, NPU, and DSP architectures.
- Deep understanding of memory bandwidth, compute bottlenecks, and hardware-aware model optimization.
Benefits
- Fun, supportive, and engaging work environment.
- Infrastructure and computational resources to support the work.
- Opportunity to work with cutting-edge technologies and leading talent.
- Opportunity to contribute to autonomous driving and transportation innovation.
- Competitive compensation package with bonus, equity, and benefits.
- Snacks, lunches, dinners, and fun activities.
Categories
About XPENG
XPENG designs, manufactures, and sells smart electric vehicles for consumers, integrating in-house advanced driver-assistance systems and connected in-car software. Founded in 2014 and headquartered in Guangzhou, it operates plants in Zhaoqing and Guangzhou, maintains a European HQ in Amsterdam, and develops eVTOL aircraft via XPENG AEROHT.