Resume

PhD in Computer Science

University of Illinois, Urbana-Champaign, IL, USA

CGPA: 4.0/4.0

• Advisor: Prof. Gagandeep Singh
• Focus: Formal Methods & Machine Learning
• Key Courses: Geometric Approximation Algorithm, Logic for Computer Science, Graph Neural Networks, Trustworthy AI Systems.

B. Tech Computer Science and Engineering

Indian Institute of Technology, Guwahati, Assam, India

CGPA: 9.69/10 (Class Rank: 2/88)

• Thesis: Dynamic Algorithm for Guarding Orthogonal Art Galleries
• Advisor: Dr. R. Inkulu
• Scholarships: Institute Merit Scholarship 2017 & 2018 of $2800 for scoring the highest grades in the academic years 2016-2018.

Verified Generation of Semantically Valid Code with LLMs

Prof. Gagandeep Singh, Assistant Professor, Dept. of CSE, UIUC

• I am currently looking into the development of programming systems with LLMs that provide users with finer-grained control over the generated output, such as code and logical formulas. On the theoretical side, I am interested in investigating the capabilities and potential limitations of LLMs in understanding code semantics.

Relational Verification of Neural Networks

Prof. Gagandeep Singh, Assistant Professor, Dept. of CSE, UIUC

• Working on developing scalable relational verification algorithms for relational properties such as monotonicity, fairness, etc. defined over multiple executions of Deep Neural Networks. The goal of this project is to enable trustworthy deployment of Neural Networks in financial and scientific applications.

Incremental Verification of Neural Networks

Prof. Gagandeep Singh, Assistant Professor, Dept. of CSE, UIUC

• Working on developing algorithms for incrementally verifying Deep Neural Networks. The goal of this project is to improve the runtime of the verification algorithm on Neural Networks after modification - weight pruning, quantization, fine-tuning, etc by using the trace of the verification algorithm on the original Neural Networks.