Summary
Pancham Banerjee is a Data Scientist with a decade of experience who blends a PhD in Extragalactic Astronomy from USC with hands-on production ML engineering at Pacific Data Integrators. He has built and deployed LLM-based RAG chatbots, semantic search engines, large-scale recommender systems and time-series forecasts for millions of utility and retail customers using PySpark, Databricks, LightGBM and deep learning. Comfortable across the full stack—from MongoDB and Docker to vector embeddings (Pinecone, Chroma) and Streamlit deployments—he pairs rigorous statistical thinking with product-focused delivery. His academic roots in computational astrophysics inform a knack for large-scale data pipelines and numerical modeling, while side projects like convnet-feature-extractor and access-spotify reveal a creative bent toward model interpretability and music analytics. Known for clear stakeholder communication and Tableau storytelling, he frequently bridges research-grade techniques and business impact to ship reliable, scalable solutions.
10 years of coding experience
2 years of employment as a software developer
Doctor of Philosophy - PhD Astronomy and Astrophysics, Doctor of Philosophy - PhD Astronomy and Astrophysics at University of Southern California
Deep Learning a 5-course specialization by deeplearning.ai on Coursera, Deep Learning a 5-course specialization by deeplearning.ai on Coursera at Coursera
Indian Institute of Technology Kanpur
Bachelor of Science (B.Sc.) Physics, Bachelor of Science (B.Sc.) Physics at University of Calcutta
English, Bengali, Hindi, Spanish