Muskan Chauhan

Aspiring Data Scientist (CDAC 2026) specializing in production-grade agentic AI systems. Engineered a LangGraph-based RAG Data Analyst with ChromaDB retrieval, BGE reranking, and dual self-correction loops — achieving 92% SQL accuracy and 0.91 RAGAS faithfulness. Across 5 end-to-end projects, delivered 71% agent self-recovery, 93% query turnaround reduction, 99% faster insight generation on 393K+ reviews, and 91% ML pipeline precision on 500K+ records via PySpark.

Proficient in LangChain, LangGraph, OpenAI API, Hugging Face, ChromaDB, BERT, XGBoost, FastAPI, and Streamlit — from prompt engineering to CI/CD-gated deployment.

RL Data Annotator – AI Training Specialist - Deccan AI Experts - Remote

(2025-08)

• Designed and validated structured spreadsheet seed datasets for synthetic prompt generation and RL Gym use cases
• Built Golden Trajectories for Excel MCP Server tasks including reasoning blocks, tool call validation and parameter verification
• Authored Agentic Trace, End State and Golden Response verifiers ensuring atomic and ground-truth-aligned quality checks
• Performed prompt validation and collaborated with QC reviewers to maintain consistent trajectory quality and task acceptance

Data Analyst - Rectra IT Infosystem Pvt Ltd - Indore

(2022-10 - 2024-12)

• Automated 6+ reporting workflows using Power BI dashboards, reducing reporting time by ~40% and saving ~8 hours/week
• Analyzed 10,000+ records using Python (Pandas, NumPy) and MySQL, driving a ~15% improvement in marketing ROI
• Performed end-to-end ETL operations including data cleaning, transformation and validation, improving data accuracy by ~22% and reducing preprocessing effort by ~30%
• Built optimized SQL queries and KPI dashboards to enable faster decision-making and improve stakeholder visibility across business functions

PG Diploma - Big Data Analytics - CDAC Mumbai (2025-02 - 2026-04)

B.Tech - Civil Engineering - People's University, Bhopal (2018-04 - 2022-09)