Manveer Singh Tamber

I am a third-year PhD student at the Cheriton School of Computer Science at the University of Waterloo, supervised by Jimmy Lin. Before starting my PhD, I completed a Bachelor’s in Computer Science at the University of Waterloo.

I work on the alignment, safety, privacy, and robustness of large language models and LLM-based agents, at the intersection of LLM safety/security and information retrieval. My goal is to make sure these systems safely serve the people who depend on them, especially when the stakes are high.

Why This Matters

People are increasingly leaning on LLMs and LLM-based agents to make decisions and take actions on their behalf. As these systems become more capable, more autonomous, and more deeply embedded in real workflows, their failures can cause real harm at scale. My research is on understanding these failures and reducing the harm they cause.