1 day ago
Shanghai, China or Beijing, ChinaIntern
Responsibilities
- Develop, train, fine-tune, and evaluate learning-based algorithms for autonomous-driving decision-making, planning, and driving behavior.
- Explore Transformer-based VLM and VLA approaches for driving-scene understanding, decision-making, and trajectory generation.
- Build Python tools and workflows for scenario mining, data cleaning, filtering, labeling, experiment management, visualization, and model evaluation.
- Analyze model failures and vehicle logs, mine hard cases, and improve dataset balance, long-tail coverage, and noise quality.
- Conduct supervised fine-tuning, reinforcement-learning, ablation, and evaluation experiments using offline metrics, open-loop replay, simulation, and vehicle-test results.
- Support model and carline adaptation across multiple autonomous-driving programs through issue analysis, validation, and scaling.
Requirements
- Currently pursuing a Master's or PhD in Computer Science, Artificial Intelligence, Robotics, Mathematics, or a related field.
- Good Python programming skills and hands-on experience with PyTorch or another deep-learning framework.
- Understanding of machine learning, deep learning, Transformer architectures, model training, optimization, and dataset analysis.
- Proficient written and verbal English communication skills and the ability to collaborate with global teams.
- Able to work at least three days per week throughout the internship.
- Experience with supervised fine-tuning, imitation learning, reinforcement learning, behavior cloning, or learning-based planning is preferred.
- Experience with VLMs, VLAs, or other multimodal foundation models is preferred.
- Familiarity with autonomous-driving datasets, trajectory data, vehicle logs, simulation, or scenario-mining pipelines is preferred.
- Strong C++ skills or relevant research, open-source, publication, or competition experience is preferred.
Benefits
- Internship with NVIDIA's autonomous-driving team.
- Work at least three days per week throughout the internship.
Categories
ML EngineeringRobotics
About Nvidia
Nvidia designs and sells GPUs and accelerated computing platforms for data centers, AI/ML, graphics, gaming, and automotive, monetizing through hardware, software platforms (CUDA, AI frameworks), and systems like DGX and networking. Customers include cloud providers, enterprises, researchers, and OEMs. Founded in 1993 and headquartered in Santa Clara, it is a public company traded on NASDAQ under NVDA.