I'm a student learning and building AI-powered systems. I code in Java, and I'm obsessed with integrating LLMs and RAG into real applications.
Currently: final year CS student @MIT Bengaluru (2027) | Preparing for SDE roles focusing on GenAI & backend systems
I build backend systems, from REST APIs to real-time code execution to AI-powered search. I care about clean architecture, solid design patterns, and actually understanding the code I ship (not just copy-pasting).
Right now I'm diving deep into Retrieval-Augmented Generation (RAG), LLM integrations, and how to make AI systems production-ready.
|
RAG-based Medical Assistant Python | FAISS | Google Gemini | Sentence-Transformers Semantic search + Gemini API. Answers medical questions by searching uploaded PDFs. This is how production RAG works. |
AI-Powered Summarizer Flask | AssemblyAI | NLTK | MongoDB Web app that summarizes news articles and YouTube videos into bite-sized summaries. Handles multi-language support, multi-modal input (text + audio), and stores summarization history. Built the backend with Flask and PyMongo. |
|
Real-time Code Runner Spring Boot | Java ProcessBuilder | REST APIs A backend service that safely executes Python code server-side and returns output in real-time. Handles process isolation, stdout/stderr capture, and timeout enforcement. Designed with clean layered architecture (Controller → Service → DTO → Model). |
Inventory Forecasting System Spring Boot 3 | PostgreSQL | JWT Auth | Spring Security Multi-warehouse inventory platform with AI-powered demand forecasting and auto-restock. Built the backend handling role-based authentication, analytics aggregations, and vendor notifications. Designed RESTful endpoints that powered an admin/manager dashboard. |
Languages: Java • Python • SQL
Backend: Spring Boot • REST APIs • PostgreSQL • JWT Authentication
AI/ML: LLM APIs (Google Gemini, OpenAI) • RAG Systems • FAISS • Embeddings
Tools: Git • Spring Security • Docker basics • ProcessBuilder
Concepts: Data Structures & Algorithms • OOP • Design Patterns • Microservices thinking
- RAG systems — semantic search, vector databases, prompt engineering
- LLM production patterns — API integration, cost optimization, fallback strategies
- Spring Boot deep dive — cloud deployment, performance tuning
Email: contactaditya013@gmail.com
LinkedIn: linkedin.com/in/contactadian
Open to: Backend SDE roles, GenAI internships, building RAG systems, or just nerding out about LLMs
Want to talk tech? Reach out. I love discussing system design, LLM integrations, and how to ship code that actually works in production.
