Anand Shenoy

Hello, I'm

Anand Shenoy

AI & ML Enthusiast

About

Passionate MSc IT student with a strong foundation in Artificial Intelligence, Machine Learning, Data Analytics and Visualization. Proficient in Python, SQL, and statistical modeling, with a current focus on applying Generative AI and Agentic AI frameworks to transform raw data into actionable intelligence. Currently seeking internships or entry-level opportunities where I can apply my skills to impactful projects and solve real-world problems.

Education icon

Education


Master of Science in Information Technology | Jul 2025 - Present | Sem I - 10 SGPI

Bachelor of Science in Information Technology | Jul 2022 - Apr 2025 | 9.27 CGPI

Higher Secondary Certificate (XII Science) | Mar 2022 | 60.00% (First Class)

Secondary School Certificate (X) | Apr 2020 | 91.20% (Distinction)

Skills

Key Projects

Project

Multi-Context Research Assistant

Built an AI agent-powered dual-workflow RAG system on n8n platform for accurate multi-document analysis using OpenAI's gpt-4o-mini, integrating automated Google Drive ingestion, Pinecone vector storage, persistent session memory, and a Streamlit frontend to ensure strict hallucination control and guarantee factually grounded research queries.




Project

Customer Feedback Routing System

Built an AI agent-powered agentic workflow on n8n platform for customer feedback analysis using Groq's compound model, integrating intelligent 5-way department classification, automated Airtable logging, real-time Slack notifications and Gmail acknowledgements to eliminate manual feedback triage entirely.




Project

Context-Aware Research Assistant

Built an AI agent-powered RAG web application for accurate document analysis using Python and LangChain, integrating Google's Gemini 2.5 Flash and ChromaDB for intelligent semantic retrieval, dynamic web search routing, and hallucination mitigation to safely query dense proprietary data.




Project

Sleep Quality Prediction

Developed a machine learning model to predict sleep quality from lifestyle data using Scikit-Learn, achieving 85.19% accuracy and an 0.88 ROC-AUC score with an optimized Random Forest classifier, validated by a custom overfitting framework.





Contact Me