Co-op Researcher-AI Autonomous Driving & Multimodal Learning

Investigate challenging problems in autonomous driving and multimodal reasoning (e.g., scene understanding, decision making, spatial reasoning, or causal learning).

Design and implement state-of-the-art algorithms using deep learning and transformer-based architectures for vision-language(-action) models.

Prototype and evaluate new ideas using internal simulation tools (e.g., CARLA, Navsim) and large-scale driving datasets (waymo, etc.)

Analyze model behaviors, develop visualizations, and contribute to benchmarking pipelines.

Collaborate closely with senior researchers to support ongoing research projects and publications.

Participate in regular technical discussions, contribute to internal presentations, and help maintain clean, reproducible codebases.

Currently pursuing a Bachelor’s degree in Computer Science, Software Engineering, Electrical/Computer Engineering, or a related field.

Strong programming skills, particularly in Python.

Familiar with deep learning frameworks such as PyTorch.

Comfortable working in a Linux environment and using tools such as Git, Docker, or Jupyter.

Knowledgeable in machine learning fundamentals — linear algebra, probability, optimization, and deep learning architectures.

Curious about or experienced in one or more of:

Computer Vision / Scene Understanding

Vision-Language(-Action) Models (VLMs, VLAs)

Reinforcement Learning or Policy Learning

Autonomous Driving Simulation / CARLA

Foundation Models and Multimodal Representation Learning