Skip to content
View vaishnavi1064's full-sized avatar
6 followers · 8 following

Block or report vaishnavi1064

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
vaishnavi1064/README.md
Vaishnavi Chaughule — AI/ML Engineer

LinkedIn Gmail GitHub

✦ mission log

role: Software Engineer & AI/ML Systems Builder
location: Seattle, WA (Open to Relocate)
education: M.S. Computer Science @ Northeastern (Khoury College)
focus: Full-Stack Systems, Agentic AI, Multi-Agent Orchestration, RAG Pipelines, MCP Integration
research: Active — Generative AI
status: Open to Summer / Fall 2026 internships

✦ orbital stack

☀️ AI/ML Core
🪐 Languages & Backend
🌌 Infrastructure

✦ star systems — projects

🪐 PersonaCR — Multi-Agent Code Review
FastAPI React TypeScript Groq Jina ChromaDB MCP

6-agent system that learns your coding fingerprint and reviews code against your own patterns not generic rules. Research-grounded in 9 papers (EMNLP, NAACL, ACL). Parallel agent execution (~48% latency savings), CRScore-inspired ML quality gate (~69ms validation). Exposes full pipeline via MCP server (SSE transport) for direct Cursor/VS Code integration. ~8.5s end-to-end.

🌍 Third-Place-Finder — AI Recommendation Engine
React TypeScript Node.js Groq Leaflet · Live Demo

Multi-stage RAG pipeline mapping natural language to structured categories, ranking top 10 with LLM rationale. Fault-tolerant integration with exponential backoff and anti-hallucination prompting. Deployed on Vercel + Render + Aiven.

🌕 OULAD Analytics Engine — Concurrent Data Pipeline
Java Multithreading BlockingQueue JUnit 5

Processes 10.6M rows at 2.1M rows/sec using producer-consumer architecture. 94% instruction coverage, 88% branch coverage with 51 tests including race condition harnesses. 3-person team.

☄️ Forest Fire Prediction — ML Risk Prediction
Python Scikit-learn Django

Wildfire prediction using 36K+ satellite records. R² improved 0.65→0.68 via RandomizedSearchCV. Model compressed from 700MB→93MB. Deployed via Django for real-time inference.

✦ flight log — experience

Role Station Mission
AI/ML Intern IBM SkillsBuild Built supervised ML models for healthcare risk prediction + IBM Cognos dashboards
Android Dev Intern Google for Developers Kotlin + MVVM apps with SQLite, REST APIs, unit & UI testing

✦ command crew — leadership

Program Manager — GameCube Club, Northeastern · Cloud Computing Lead — Google Developer Groups · Event Co-Lead — GDSC

✦ signal map

Popular repositories Loading

  1. PersonaCR PersonaCR Public

    Research-grounded multi-agent AI system that reviews code against your team's personal coding patterns, generates documentation, and tracks quality over time. Chat-first with MCP.

    TypeScript 1

  2. vaishnavi1064 vaishnavi1064 Public

  3. Chatbot Chatbot Public

    Jupyter Notebook

  4. Sentiment-Analysis-using-NLP Sentiment-Analysis-using-NLP Public

    Python

  5. Bank-Customer-Churn-Prediction-using-H2O-Auto-ML Bank-Customer-Churn-Prediction-using-H2O-Auto-ML Public

    Jupyter Notebook

  6. Parkinson-s-Disease-Prediction Parkinson-s-Disease-Prediction Public

    Jupyter Notebook