Hi, I'm Karan.
I'm a Computer Science Ph.D. Candidate at Georgia Institute of Technology, working under the guidance of Prof. Ashok Goel, director of the Design & Intelligence Lab and AI-ALOE Institute.
My research focuses on creating, deploying, and comprehensively evaluating conversational AI tools, both from technical and human-centered perspectives. I'm expecting to graduate in May 2026 and I'm actively seeking Applied AI Research and Engineering roles that focus on building AI tools and agentic AI systems. I'm also interested in startups, reach out to me if you want to work together and build something together!
Before Georgia Tech, I graduated from Indian Institute of Technology Bombay in July 2020 with Bachelors and Masters in Electrical Engineering. I specialized in Signal Processing for my masters and also completed a minor in Computer Science and Engineering.
My first name is pronounced like Curren as in Current. My pronouns are he/him/his.
Research
Conversational AI
Developing interactive grounded agentic AI systems
Educational Technology
Creating AI-powered tools to enhance learning experiences
Human-Computer Interaction
Designing engaging interfaces for human-AI collaboration
Recent Updates
- October 2025
My recent project MuDoC has been deployed as the new Jill Watson in Prof. David Joyner's Knowledge-based AI course in Georgia Tech's OMSCS program. Watch the intro video here! - July 2025
I presented our work 'Towards a Multimodal Document-grounded Conversational AI System for Education' at the 26th International Conference on Artificial Intelligence in Education (AIED 2025) in Palermo, Italy. - May 2025
My collaborator Anjali Singh presented our work 'Protecting Human Cognition in the Age of AI' at the Tools for Thought Workshop at CHI 2025 in Yokohama, Japan. - April 2025
🎉 PhD Milestone! I passed my PhD Proposal exam on 16th April, 2025! My thesis title is "Conversational AI for Education: Design, Evaluation, and Continual Improvement". Expecting to graduate in May 2026. - March 2025
I presented our work 'MuDoC: An Interactive Multimodal Document-grounded Conversational AI System' at the Machine Learning and Knowledge Engineering for Trustworthy Multimodal and Generative AI (AAAI-MAKE 2025) in San Francisco, California, US. - November 2024
I presented our work 'Can Active Label Correction Improve LLM-based Modular AI Systems?' at the 2024 Conference on Empirical Methods in Natural Language Processing in Miami, Florida, US.
Get In Touch
I'm always interested in new opportunities and collaborations. Feel free to reach out over Email or LinkedIn.