Data Science Student, IIT Madras
I'm a Data Science & Applications student at IIT Madras, focused on building high-performance LLM orchestration systems, scalable machine learning pipelines, and full-stack web applications.
Every project is getting its own live demo. Some are ready to explore now, with the rest on the way.
LLM routing gateway dispatching queries across a 5-tier model matrix with pre-execution adversarial guardrails. Evaluated on 700 RouterBench and LMSYS queries, achieving an estimated 84.06% cost reduction vs. flagship, neutralizing 56.78% of prompt injection attempts with zero false alarms.
Dual-FAISS RAG pipeline retrieving into a quantized Gemma-4-12B. Achieved top score (0.75893 MAP@3) on Kaggle. Tracked 47 experiments on WandB.
Engineered an ML pipeline with TF-IDF and metadata preprocessing to predict comment categories. Evaluated multiple classifiers achieving macro F1 0.8175.
Role-based recruitment application spanning 3 dashboards. Automated recurring reminders and reporting jobs with Redis and Celery.
Multi-user quiz platform featuring secure authentication, dynamic quiz management, and real-time Matplotlib-based performance tracking.
Official cloud and professional credentials.
Academic programs and coursework.
The stack I reach for, grouped by what I use it for.
Feel free to look around, break things (it's okay, I'll fix it later), and if any doubt or query strikes, get in touch.
