Research
What I work on
My research sits at the intersection of representation learning and biology: designing models that are accurate, efficient, and interpretable enough to trust in a clinical setting.
Single-cell genomics
Inductive graph neural networks for imputation, clustering, and trajectory inference on sparse, noisy scRNA-seq atlases.
Generative & structured models
Graph transformers, VAEs, and masked transformers that capture position and structure relationships in biological sequences and networks.
Knowledge-grounded AI
Ontology and knowledge-graph grounded LLMs for interpretable, traceable clinical decision support and differential diagnosis.
Highlights
Recent news
- Jun 2026Joining PopVax, Hyderabad as a Machine Learning Scientist, working on ML for vaccine and therapeutic design.
- Jun 2026Submitted "Adapting Indic Text-to-Speech for the Real World", a survey of architectures and an industrial-grade benchmark.
- May 2025Joined ConvoZen AI, NoBroker as an Associate Data Scientist on the voice stack.
- Apr 2025Joined the CRIS Lab at Columbia University as a Project Member, working on knowledge-graph-grounded LLMs for differential diagnosis.
- 2025First-author paper published in Computers & Chemical Engineering on inductive GNNs for scRNA-seq imputation.
- 2024Research Intern at the CPSWin Lab, Kansas State University, building a VAE + LTMG framework for glioblastoma analysis.
Selected work
Featured publication
-
Journal · 2025
Inductive graph neural network framework for imputation of single-cell RNA sequencing data
Computers & Chemical Engineering, vol. 195 (2025), 109031
Background
Education & skills
B.S. & M.S. in Biological Sciences
- Specialization: Computational Biology
- Thesis: Bioinformatics, graph neural networks, and generative modeling for scRNA-seq