Soumendu Bhattacharjee, Ph.D Physics

Fine-tuned LLM models for classification tasks using Azure DevOps. Performed multi-label classification on large healthcare documents stored in Azure Blob using Spark. Used Azure Data Factory to automate preprocessing pipelines and summary generation workflows.

Provided supply chain optimization solutions. Integrated large language models (LLMs) with knowledge graphs for enterprise content navigation. Enhanced RAG system performance using a graph-based approach. Built Q&A systems for complex documents and report generation for legal documents and news articles using LLMs. Finetuned LLMs using LoRA and ran LLMs locally with Ollama. Built a RAG Agent for Q&A on tabular data. Developed a LangGraph research agent. Performed web scraping and data cleaning for LLM input. Led the data science team and addressed diverse business problems. Deployed code using Docker and FastAPI. Worked with MongoDB, Redis, Kafka, and Postgres for real-time content streaming. Built and deployed Streamlit apps using data from S3, Azure Blob, and SFTP. Managed team operations and orchestrated jobs using Airflow and Cron scheduling. Performed speech-to-text analysis on customer support data and conducted A/B testing.

Led projects on fault detection in PV systems using autoencoder models. Supervised teams for long-term GHI prediction using multivariate LSTM, XGBoost, and CatBoost. Managed connector fault detection projects using Boosting, RFC, and SVM. Applied Fourier transform for noise reduction. Converted tabular data into images for classification using MobileNet, CNN, VGG16, and VGG19. Generated synthetic time series data using Gretel and TimeGAN. Conducted anomaly detection, feature selection, and simulation of PV systems. Presented work to clients and trained ML models on AWS SageMaker. Used AWS S3 and Glue for data pipelines, stored results in Snowflake and Redshift, and scheduled batch evaluations with Airflow.

Performed classification on tabular datasets using Random Forest, Boosting, LightGBM, and SVM. Conducted image classification with deep neural networks (InceptionV3, ResNet50, MobileNet, CNN, VGG16, VGG19, EfficientNetB7). Worked on image segmentation for biological images using UNet and Stardist. Conducted feature selection, model optimization, and hyperparameter tuning. Developed automated systems for classification from raw spectroscopic data. Analyzed tabular data by converting to images with Tab2Img. Performed denoising with Fourier analysis. Supervised junior members and presented results to technical and non-technical audiences. Conducted text data analysis and time series analysis. Built pipelines integrating SQL Server, BigQuery, and Duck DB. Used S3, MongoDB, and Redis for hybrid cloud-data storage workflows.

Analyzed data and optimized ML models (supervised and unsupervised) for large-scale scientific experiments. Developed and implemented controls and electronics for detection systems. Prepared scientific proposals and documentation, and presented analysis results at conferences. Collaborated with global groups and supervised junior members.

Analyzed data and optimized ML models for large-scale scientific experiments. Published results in high-impact journals. Maintained and improved hardware and software equipment. Managed experimental campaigns and prepared scientific proposals and documentation. Supervised undergraduate and master students and collaborated with group members.

Analyzed data and optimized ML models for large-scale scientific experiments. Published results in high-impact journals. Prepared scientific proposals and documentation, and presented results at conferences. Supervised undergraduate and master students and collaborated with other groups. Conducted Monte Carlo simulations for gamma ray detectors using C++.