Skip to main content

Mentor Areas

Distributed and Operating Systems
Cloud Infrastructure
Internet and Web Systems

Description:

We aim to build the next generation of agentic AI browsers -- systems like OpenAI Atlas or Perplexity Comet -- with much faster performance while maintaining high accuracy.  Recent advances in AI browser use have enabled users to leverage AI to assist in more general web-related tasks than simple text generation, but the process is typically very slow.   Our project focuses on fundamental advances in model-serving engines specialized for multimodality and web interaction, as well as novel ML architectures for AI browser tasks.

Development will involve new model architectures, serving systems such as vLLM and SGLang, next-generation agent browsers, and web-search task benchmarks as part of a broad open-source effort toward building faster and better agentic AI browsers.

Preferred Qualifications

Extensive programming experience (particularly in Python)
Experience with building systems and optimization for performance and scalability
Familiarity with website architectures (e.g., HTML, Javascript, DOM trees)

Project Website

Learn more about the researcher and/or the project here.
https://vincen.tl

Details:

Preferred Student Year

Second-Year, Junior, Senior

Academic Term

Fall, Spring, Summer

I prefer to have students start during the above term(s).

Volunteer

Yes

Yes indicates that faculty are open to volunteers.

Paid

No

Yes indicates that faculty are open to paying students they engage in their research, regardless of their work-study eligibility.

Work Study

No

Yes indicates that faculty are open to hiring work-study-eligible students.

Researcher


Associate Professor