M.S. Computer Science · Emory University · Class of 2026
Open to AI/ML, data engineering, and SWE roles.
I build AI systems across data engineering, deep learning, and production software, from sub-second analytics on 385M events to biomedical RAG and medical image enhancement. Currently researching digital health at the Emory FIT Lab, with a focus on teams where rigorous engineering meets real-world impact.
My research explores how large language models and deep learning can be applied to real-world problems in healthcare and science. Current focus areas: retrieval-augmented generation for domain-specific QA, medical image enhancement, graph neural networks, and digital health monitoring using passive technology interaction data.
A topology-aware code review system that fuses deterministic static analysis with specialized LangGraph agents. Instead of dumping raw files into an LLM, CodeNexus builds an AST-driven project graph so agents can reason over imports, call chains, inheritance, security risks, and developer rationale with precise codebase context.
A reproducible research framework for studying whether coding agents can improve through execution feedback. CodeSelf converts benchmarks into canonical tasks, runs generated Python in a sandbox, scores correctness-first rewards, and scaffolds GRPO/PPO experiments with held-out statistical evaluation.
A browser-based Python execution visualizer that makes runtime behavior spatial. Paste code, run it with Pyodide, and scrub through line-by-line traces of scopes, variables, references, loops, function calls, object mutations, stdout, and errors.
A reproducible lab for domain-adaptive language model experiments. Retcon turns local corpora into config-hashed training and evaluation artifacts, then tracks LoRA runs, checkpoint evaluations, contamination checks, forgetting signals, provenance, and reports.
Extended Pix2Pix with self-attention for chest X-ray quality improvement on NIH ChestX-ray14. Built synthetic degradation pipeline for paired training data.
A second-order optimizer using the Fisher Information Matrix that beats Adam and RMSProp on MLPs. Applied Nyström approximation and Kronecker-factored preconditioning with JAX-style JIT compilation.
Abstractive summarization pipeline for arXiv papers using google/pegasus-pubmed. Trained on 1,000 papers with beam search decoding. Published model on Hugging Face.
LLM-powered personal dietitian for diabetes management. Generates personalized meal recommendations with glycemic index verification and portion size calculations against clinical guidelines.
Document relationship modeling on CORA using Graph Neural Networks. Compared GCN, GAT, and GraphSAGE architectures for citation prediction and clustering.
Retrieval-augmented biomedical QA on PubMedQA. Dense retrieval with BioBERT + FAISS, re-ranking with BM25/ColBERT/MonoT5, and LoRA fine-tuned T5 generator.
XNLI 2.0: Improving XNLI Dataset and Performance on Cross-Lingual Understanding
IEEE 8th I2CT Conference · 2023
Jan 2025 – Present
Graduate Research Assistant
Emory FIT Lab · Atlanta, GA
Jan 2026 – Present
Graduate Teaching Assistant
Emory University · Atlanta, GA
May 2025 – Oct 2025
VP, International Student Affairs
Graduate Student Government Association (GSGA)
Feb 2025 – Aug 2025
International Student Liaison
Emory University, Laney Graduate School
Oct 2024 – Dec 2025
Proctor
Emory University, Office of Undergraduate Education