Sagandeep Kaur

I’m a Data Science student at IIT Madras (B.S. Data Science & Programming) with a strong track record of building production-minded systems. I’ve earned a CGPA of 9.04 and consistently push projects from prototype to reliable deployment.

As a Web Development Intern at NPTEL, IIT Madras, I optimized complex SQL for large-scale reporting, deployed production-grade Flask REST APIs, and automated backend data pipelines using PHP and SQL. I also implemented automated validation routines to ensure backend data quality and schema compliance across live pipelines.

In my NLP Engineering Internship (IIT Madras), I engineered preprocessing pipelines to turn messy text into clean schemas and built internal data visualization components to extract actionable insights from high-dimensional datasets. I also served as a Teaching Assistant (Computer Science), mentoring 100+ students in Python, algorithms, and software engineering practices.

My projects blend NLP, scalable infrastructure, and reliability. I architected a Distributed MLOps & Infrastructure Pipeline using FastAPI, Docker, GitHub Actions, GKE, HPA, OpenTelemetry, DVC, and MLflow—plus safeguards against prompt injection. I’ve also built a FAISS-powered document QA engine, and end-to-end multilingual sentiment and speech pipelines using Gemma LLM and Whisper/Faster-Whisper.