AI/ML & Full-Stack Engineer · B.E. CSE (AI & ML) @ CBIT, Hyderabad · Class of 2027 Currently researching EEG-based cognitive fatigue detection @ NIT Goa
I build systems that sit at the intersection of machine learning research and production software — fine-tuning transformer models, then shipping them as real, working applications rather than notebooks. My recent work spans sentiment and emotion detection with DistilBERT, multilingual text classification with XLM-RoBERTa across five Indic languages, and fraud detection with explainable AI.
Right now I'm at NIT Goa researching EEG-based cognitive fatigue prediction, working through physiological signal preprocessing, feature engineering, and model evaluation as part of a paper in progress. Outside of research, I lead CBITMUN as Secretary-General, coordinating a 200+ member team through one of the largest student-run MUN conferences in the region.
What ties it together: I care about the full lifecycle of an ML system — training, evaluation, deployment, monitoring, and explainability — not just the model. I'm graduating in 2027 and open to full-time opportunities from July 2026.
|
Full-stack NLP application for sentiment and emotion analysis, built end-to-end from model training to production release.
|
XLM-RoBERTa fine-tuned across five Indic scripts to classify news into ten categories.
|
|
Hybrid fraud detection system combining ML and rule-based risk fusion for real-time transaction screening.
|
Production website for a national-level Model United Nations conference, built and maintained while serving as Secretary-General.
|
Languages
AI / Machine Learning
Backend & APIs
Frontend
Tools & Infrastructure
Cloud & Deployment
AI Research Intern — National Institute of Technology Goa June 2026 – Present
Developing deep learning models for EEG-based cognitive fatigue prediction, running end-to-end experimentation across physiological signal datasets — preprocessing, feature engineering, and model evaluation. Contributing to a research paper through result validation, technical documentation, and scientific writing, informed by a systematic literature review of state-of-the-art fatigue detection approaches.
