Tanuj Kumar Verma

Developing a platform using Microsoft Azure AI Search to interact with documents stored in Azure Blob Storage and SharePoint. The platform creates indexes and uses skillsets to enhance response accuracy. Integrates with Azure OpenAI for query processing, providing a chat playground for user interaction.

Conducted Extensive Research on Small Language Models that can run CPUs without requiring GPUs. Developed a RAG Application in order to analyze accuracy and the period of time acquired by disparate Small Language Models to give responses while running on CPUs rather than GPUs.

Developed an online CV processing system utilizing Azure services and machine learning models for efficient document analysis and user query handling. Implemented an offline CV evaluation system using Streamlit, integrating advanced ML algorithms to process multiple CVs concurrently. Deployed the CV parser model on an EC2 server via SCP, integrating GitLab for version control and secure code management.

Developed YoloV5 Models for Image Labelling, specifically for Identity and non-Identity cards. Created an Address Parser using Python to process Australian Addresses. Implemented an Invoice Parsing System leveraging PyTesseract and Regex to accurately extract and categorize entities.

Managed Monthly Invoice Coordination at Alkem Pharmaceuticals, utilizing Python for accurate data extraction and handling of rejected invoices. Maintained detailed Excel records of coordinate fixes and conducted Product Matching to ensure precision in Medicine Name Identification.