Aditya Padale

AI & Data Science Engineer · Generative AI, RAG & Multi-Agent Systems

Sangli, Maharashtra, India

@aditya_padale

GitHub LinkedIn

0 followers

🎓 B.Tech in Artificial Intelligence and Data Science at Shivaji University Kolhapur · Graduating 2027

About

AI & Data Science Engineer with hands-on experience building Generative AI, multi-agent systems, RAG pipelines, machine learning solutions, and full-stack applications. Strong foundation in Python, AI/ML, backend engineering, and cloud technologies, with a focus on scalable, production-oriented problem solving.

Experience

AI Intern

Zanvar Group

Apr 2025 – Jun 2025

Creating a RAG chatbot. Built a Retrieval-Augmented Generation (RAG) system to process large-scale manufacturing data from Excel/CSV files, enabling instant natural-language insights for non-technical teams. Integrated the OpenAI API with a vector database to generate context-aware answers from enterprise data, reducing manual reporting effort by over 60%.

Education

2027

B.Tech

Annasaheb Dange College of Engineering, Ashta

Artificial Intelligence and Data Science · Aug 2023 – Aug 2027

Artificial Intelligence and Data Science · Aug 2023 – Aug 2027

Skills

3 to 6 months

Python FastAPI LangChain Vector Databases Retrieval Augmentation Generation

<3 months

C Go SQL LLMs React Faiss OpenCV Node.js PyTorch Next.js JavaScript TensorFlow Tailwind CSS scikit-learn Model Deployment API Integration Understanding

Tools / apps / platforms

3 to 6 months

Microsoft Excel

<3 months

Git Docker GitHub MongoDB ChromaDB PostgreSQL Hugging Face

Projects

College Discovery Event Website ↗

Full-stack development

Designed and developed a full-stack event discovery and registration platform featuring 24 technical and non-technical events, and integrated a secure payment gateway that processed 3,000+ student transactions worth ₹3,00,000+ with zero reported failures.
Adaptive Multi-Agent Coordination System ↗

Python, multi-agent systems

Designed a confidence-weighted agent selection algorithm with adaptive memory and a Verifier Agent, improving task success rate by 23% and reducing redundant LLM calls by 31% against a static-routing baseline across 50 benchmark tasks.
Multi-Agent Research Debate System ↗

Python, OpenAI, Anthropic, Ollama

Engineered a Python-based Multi-Agent AI framework enabling task decomposition, intelligent agent selection, DAG-based parallel execution, adaptive orchestration, inter-agent communication, and LLM-powered validation with OpenAI, Anthropic, and Ollama support.

🏆 Achievements & awards

ADCET Hackathon Season 3 - 1st Runner Up · 2026

⚽ Extracurricular activities

Technical Lead – Discovery
Technical Head – AI&DS Department Association
Vice President – Nexus Club

Explore the Broxer community

💬 Q&A Ask about roles, salaries and interviews — and help others. 👥 Circles Join discussions on skills, companies and industries. 📰 Feed Follow updates and insights from the community.