About

Pranjal Sahu is a Data Scientist at Delhivery with a passion for solving problems with data. He specializes in dealing with text and speech data to make sense out of it, training machine learning models to process natural language, deploying them to production, and explaining them. Pranjal has a promising publication track record and skills to build relationships as well, not just models. With almost a year of professional experience working in the Research and Development of Machine Learning systems, Pranjal has worked on research topics in and around specific use-cases of AI in CV/NLP. He has worked on decoding sales conversations, structuring insights using unstructured data, and information extraction from raw speech text. Pranjal has deployed ML models for multiple product use cases, using Docker, AWS services, and FastAPI. He has also built automated pipelines on GCP for training and evaluating S2T models on a continuous basis. Pranjal has worked primarily on Python (Flask and FastAPI) for development, AWS Suite (Fargate/Lambda/S3, etc.) for cloud services, and Docker for packaging deployment modules. He has also worked on Databricks, ElasticSearch, AWS, Snowflake, and other tech stacks. Pranjal has a Bachelor of Technology in Electrical, Electronics, and Communications Engineering from the Indian Institute of Information Technology, Sri City. Pranjal's tech stack includes Research Scientist, ML, Data Scientist, NLP, AWS, AI, Docker, Snowflake, Python, Deep Learning, Pytorch, Web, Flask, GCP, Computer Vision, SQL, Text Classification, SVM, XGBoost, Keras, Seaborn, Databricks, language models, Scikit, test, Pandas, Neural Networks, NoSQL, Elastic Search, Search, and Software Engineer.