Ashirwad R.

Key Skills

Software

Other

Top Subject Matter

Marketing datasets and business analytics data (Google Sheets)

Multimodal GenAI question answering over PDFs and YouTube content

Top Data Types

Text

Document

Video

Top Task Types

Data Collection

Prompt + Response Writing (SFT)

Freelancer Overview

Data Champion Intern | DeepThought (3 Months) — Data automation and dataset preparation. Brings 2+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other and Pinecone. Education includes Bachelor of Technology (Honours), Chhattisgarh Swami Vivekananda Technical University (2026) and Senior Secondary (XII), S.P. Jain College (BSEB) (2020). AI-training focus includes data types such as Text and Document and labeling workflows including Data Collection and Prompt + Response Writing (SFT).

Labeling Experience

Data Champion Intern | DeepThought (3 Months) — Data automation and dataset preparation

OtherTextData Collection

Built and validated automated ETL pipelines using Python, performing CRUD-style dataset updates through the Google Sheets API. Curated marketing datasets and derived insights to improve data processing efficiency and reduce manual work. Supported data synchronization by preparing inputs for visualization tools used by stakeholders. • Automated ETL using Python scripts and CRUD operations via Google Sheets API. • Applied data validation steps to ensure quality of updated records. • Analyzed marketing datasets to derive business-relevant insights. • Created data visualization tools to synchronize data across platforms.

2025

RAG-Powered Study GenAI Assistant — RAG system development

DocumentPrompt + Response Writing (SFT)

Developed a multimodal Retrieval-Augmented Generation (RAG) assistant that answers user queries using information extracted from PDFs and YouTube videos. Implemented an embedding-based semantic search pipeline with Pinecone to retrieve relevant context for generation. Designed an OOP-style modular architecture to handle concurrent inputs including text, images, and video links. • Integrated Pinecone vector database for embeddings and high-speed semantic search. • Enabled RAG responses grounded on content from PDFs and YouTube videos. • Built modular input handling for video links, images, and text. • Implemented API integration to support retrieval and question answering workflows.

Not specified

Education

Work History