Applied Deep Learning Algorithm Intern

We are looking for a highly motivated Applied Deep Learning Algorithm Intern to join our autonomous driving team. You will work with experienced engineers on learning-based driving algorithms, supervised fine-tuning, reinforcement learning, data optimization, model evaluation, and multi-carline adaptation.

Responsibilities:

• Develop, train, fine-tune, and evaluate learning-based algorithms for autonomous driving decision-making, planning, and driving behavior.
• Explore Transformer-based approaches, including VLMs and VLAs, for driving-scene understanding, decision-making, and trajectory generation.
• Build supervised fine-tuning data workflows and Python tools 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, including 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.
• Good understanding of machine learning, deep learning, Transformer architectures, model training, optimization, and dataset analysis.
• Proficient English communication skills, both written and verbal, with the ability to collaborate effectively with global teams.
• Able to work at least three days per week throughout the internship.

Nice to Have:

• Experience with supervised fine-tuning, imitation learning, reinforcement learning, behavior cloning, or learning-based planning.
• Experience using or fine-tuning VLMs, VLAs, or other multimodal foundation models.
• Familiarity with autonomous driving datasets, trajectory data, vehicle logs, simulation, or scenario-mining pipelines.
• Strong C++ skills or relevant research, open-source, publication, or competition experience.