I'm Prasad Kadam, a last-year Information Technology Engineering student at Progressive Education Society's Modern College of Engineering, Pune, graduating in 2027.

I'm primarily interested in the engineering behind applications:

backend systems → AI/LLM applications → infrastructure → deployment

I enjoy building systems where AI isn't just a chatbot, but can actually retrieve information, use tools, interact with databases, make decisions and execute workflows.

Currently focused on:

• 🤖 Agentic AI & LLM applications
• ⚙️ Backend engineering with Python & FastAPI
• 🔎 RAG, semantic search & retrieval systems
• 🐳 Docker & Kubernetes
• ☁️ Cloud-native development
• 🧠 Data Structures & Algorithms
• 🏗️ Building practical engineering projects

An end-to-end Agentic AI customer support platform combining LLMs, Hybrid RAG, real business data and backend tools.

• 🧠 ReAct-based agent workflow
• 🔧 Tool registry & tool execution
• 🔎 Hybrid RAG
• 📚 FAISS semantic retrieval
• 🔤 BM25 lexical retrieval
• 🎯 Cross-encoder reranking
• 🧾 Order lookup
• 🎫 Support ticket lookup
• 📊 SQL analytics
• ✉️ Email generation
• 💭 Conversation memory
• 🔌 Gemini & Groq provider abstraction
• 📡 SSE streaming
• 🔐 JWT authentication
• 🗄️ PostgreSQL + Alembic
• 📈 Evaluation framework

Stack

Python FastAPI PostgreSQL FAISS BM25 Sentence Transformers Gemini Groq React TypeScript Vite Tailwind CSS

Deployment

Railway · Vercel

Kubernetes / DevOps tooling focused on diagnosing and understanding running services.

A backend-oriented project exploring how Kubernetes information can be surfaced programmatically instead of relying entirely on manually jumping between kubectl commands.

• Kubernetes service discovery
• Pod diagnostics
• Deployment monitoring
• Kubernetes API interaction
• Docker
• kind
• kubectl
• Infrastructure troubleshooting

Stack

Python Kubernetes Docker kind kubectl

Final Year Project

An intelligent data-pipeline project focused on understanding how changes in upstream data can affect downstream systems.

• Data lineage
• Data dependencies
• Semantic drift
• Data quality
• Pipeline monitoring
• Impact analysis
• AI-assisted analysis

Status: In Progress

Backend REST API with authentication, task management, PostgreSQL persistence and database migrations.

Stack

Python FastAPI PostgreSQL SQLAlchemy JWT Alembic Render

🤖 AI / GenAI

LLMs · Agentic AI · RAG · ReAct · Tool Calling · FAISS · BM25
Embeddings · Semantic Search · Hybrid Search · Cross-Encoder Reranking
Sentence Transformers · Prompt Engineering · Context Engineering · Gemini · Groq

⚙️ Backend & Languages

Python · Java · JavaScript · TypeScript · SQL
FastAPI · Node.js · Express.js · REST APIs · JWT

🗄️ Databases

PostgreSQL · MySQL · MongoDB

☁️ Cloud & DevOps

Docker · Kubernetes · kubectl · kind · Linux
GitHub Actions · Railway · Vercel · Render · CI/CD

📊 Data & Machine Learning

NumPy · Pandas · Matplotlib · Seaborn · Scikit-learn
Jupyter · Hadoop · CloudSim · Machine Learning · Data Science · Big Data

🎨 Frontend

React · TypeScript · Vite · Tailwind CSS · HTML · CSS

🛠️ Developer Tools

Git · GitHub · VS Code · PyCharm · Anaconda · Jupyter Notebook

Worked on practical web-development tasks involving:

HTML · CSS · JavaScript · APIs

Projects included:

• Interactive navigation menu
• Stopwatch application
• Tic-Tac-Toe
• Personal portfolio website
• Weather API application

This experience helped me build a foundation in web development before moving deeper into backend engineering and AI systems.

Currently preparing for software engineering placements through consistent practice in:

Data Structures · Algorithms · Problem Solving · Algorithmic Patterns · Aptitude

My current learning philosophy is simple:

Build something → break something → understand why → fix it → build again.

Backend Engineering · AI / GenAI · Agentic Systems · Kubernetes