Skip to content
View Aharshi3614's full-sized avatar

Block or report Aharshi3614

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Aharshi3614/README.md

Hi πŸ‘‹, I'm Aharshi

AI/ML Engineer in the making | Building RAG systems, chatbots & forecasting pipelines

Aharshi3614


πŸš€ About Me

  • πŸŽ“ 3rd-year B.Tech CSE (AI & ML) @ IEM Kolkata, 2023–2027
  • 🌟 Google Gemini Student Ambassador
  • πŸ› οΈ Active contributor @ SSoC Season 5
  • πŸ† Built DevWhisper at HackBLR 2026 (Geek Room) β€” reached pre-finals out of ~500 teams
  • πŸ“Š Worked on demand forecasting with XGBoost (RΒ² = 0.967) @ Evoastra Ventures
  • πŸ” Currently looking for paid AI/ML/backend/full-stack internships β€” open to opportunities!

πŸ”§ Tech Stack


πŸ“Œ Featured Projects

πŸ—£οΈ DevWhisper

Voice-first AI dev assistant built solo at HackBLR 2026. Stack: Vapi, FastAPI, Groq/LLaMA 3.3 70B, Qdrant, Deepgram. Reached pre-finals out of ~500 teams.

πŸ”— Repo β€’ πŸŽ™οΈ Live Demo

πŸ“¦ Supply Chain Demand Forecasting

XGBoost-based forecasting pipeline (RΒ² = 0.967, RMSE = 20.87), deployed via FastAPI + Docker, full report with branching strategy and CI/CD.

πŸ”— Repo β€’ πŸ“Š Live App

🏏 IPL Win Predictor

Logistic Regression model predicting live match win probability, deployed with Streamlit.

πŸ”— Repo

πŸ“Š GitHub Stats


Open to paid internships in AI/ML, Backend, and Full-Stack roles πŸš€

"Shipping fast, learning faster."

Pinned Loading

  1. supply-chain-analytics-capstone supply-chain-analytics-capstone Public

    Jupyter Notebook 1

  2. Devwhisper Devwhisper Public

    DevWhisper is a voice-first AI agent built for developers. Instead of stopping to search through files or documentation, you just ask out loud β€” and it answers based on your actual codebase.

    Python