Project Overview

We are seeking 2-3 highly motivated research interns interested in advancing the state of the art in Embodied AI, Large Language Model (LLM) Agents, and Autonomous Systems at SMART.

With the rapid evolution of Generative AI, research interns will assist researchers in investigating how to develop next-generation LLM-based Agents and World Models that enable safe and trustworthy autonomy. Our goal is to bridge the gap between high-level reasoning and low-level control in complex urban environments. We are specifically interested in, but not limited to, the following research topics:

• LLM Agents for Autonomy: Utilizing LLMs for planning, reasoning, and decision-making in autonomous driving and robotics.
• World Models & Generative Simulation: Building data-driven world models for video generation, future prediction, and closed-loop simulation.
• Embodied AI: Integrating vision, language, and action to create intelligent agents capable of interacting with the physical world.

Responsibilities

• Develop and benchmark LLM-based decision agents, including chain-of-thought reasoning, structured memory, and planning modules.
• Implement and train world models for spatiotemporal prediction, simulation, and autonomous driving or mobility applications.
• Build reproducible research pipelines and assist with experiments, ablation studies, and model diagnostics.
• Collaborate with research staff and graduate students to prepare publications for top conferences and journals in AI, robotics, and transportation.

Requirements

• Currently pursuing a Bachelor’s or Master’s degree in Engineering, Computer Science, Data Science, Robotics, AI/ML, or related fields.
• Strong interest in LLM agents, autonomous systems, world models, or risk-aware decision making.
• Proficiency in Python, deep learning frameworks (PyTorch, Transformers, JAX preferred), and modern AI toolchains.
• Experience in one or more areas such as LLM/MLLM reasoning, world models, multimodal learning, etc. is a plus.
• We welcome students of all experience levels, as long as you are motivated, proactive, and willing to learn.

The internship must be approved by the University.