Yash Bhaskar Email & Phone Number

Hyderabad, IN

Canada

Hyderabad, Telangana, India

Hyderabad, Telangana, India

Conducted research on North American footfall data, developing data scraping pipelines and utilizing Google Cloud Geocaching and Bing Distance Matrix APIs for spatial analysis.

California, United States

• Clearedge - Data ingestion for LLMs
• Developed Clearedge.ai, an open-source Python library for LLM data ingestion, implementing text and metadata extraction from complex scanned pdf and other file formats.
• Analyzed document segmentation and OCR solutions like Tesseract, PaddleOCR, DocTR, Microsoft TableBank and YoloV9. Implemented Clearedge’s core pipeline for text, image, and table data extraction.Code Indexer
• Created a code query system for large repositories using tree-sitter, enabling semantic analysis of functions across multiple files.
• Implemented a code snippet ranking system using PageRank and leveraged GPT-4o for response generation. I designing the core logic and deployed its backend.

Delhi, India

• Partnered with Qdrant and Astria.ai for technical content creation, producing in-depth articles on their platforms’ applications in enterprise cloud-based RAG systems and virtual staging using custom diffusion models.
• Made articles on RAG Pipelines, Vector Databases, Distributed RAG System using RAY, ReAct Agents in RAG, DocumentationRAG System with Internet Access.

Hyderabad, Telangana, India

• Built a validation layer, flagging a portion of output for enhanced correctness checks.
• Redesigned the PDF Parser for accurate text detection, resulting in a reduction in errors.

Btech In Computer Science And Ms In Computational Linguistics, Computer Science

Class 12, 95.6 %

Class 10, 97.6 %