Looking for a job

Hamsini K

@hamsinik

Message

I build data pipelines and AI retrieval systems that turn raw data into measurable outcomes.

India

Message

What I'm looking for

I’m looking to apply my data science, machine learning, PySpark, and Generative AI foundation to real-world analytics problems, including opportunities such as American Express's AIM team.

I’ve built a PySpark ETL pipeline on a Spotify dataset processing more than 1.6 million records, taking raw audio data through feature engineering, modeling, and validation.

I compared K-Means, Agglomerative Clustering, Logistic Regression, Random Forest, and SVM approaches to predict song popularity, reaching up to 87.3% accuracy.

I also built a RAG document intelligence system with Python, LangChain, HuggingFace, semantic search, and vector embeddings to retrieve relevant information from large document collections. I iteratively tuned retrieval quality toward a more business-relevant outcome.

Alongside data and AI work, I built and tested a URL shortener REST API using FastAPI, SQLite, and pytest. I’m eager to bring my foundation in analytics, machine learning, and Generative AI to data-focused teams.

Experience

Work history, roles, and key accomplishments

Current

B.Tech Computer Science Engineering (AI) Student

Current

Amrita Vishwa Vidyapeetham

Jan 2022 - Present (4 years 8 months)

Final-year B.Tech student with hands-on experience in PySpark, Python, and machine learning, including building a distributed ETL pipeline and a RAG-based document intelligence system.