Skip to main content
Swaraj Chattaraj AI Engineer & Developer

Building AI systemsthat go beyond demos.

I am Swaraj Chattaraj, an AI Engineer specializing in agentic workflows, self-correcting RAG loops, and production-grade reasoning architectures. I bridge the gap between probabilistic models and deterministic software engineering.

System Specifications
5-Stage LangGraph stateful orchestrator
63 % Latency reduction via concurrent asyncio
95 % Retrieval precision via Hybrid RAG routing
100 % Test coverage on state-machine logic

Core Research &Development Focus

I focus on building production-style AI tools. My work centers on self-correcting RAG systems, structured data outputs, and evidence-provenance metrics, bringing developer rigor to probabilistic AI workflows.

01
Agentic AI & RAG

Designing multi-stage graph loops using LangGraph (Planner → Retriever → Synthesizer → Critic) that process queries like human analysts.

02
Corrective Verification

Engineering self-correcting loops where a Critic agent verifies claims against grounding materials, triggering supplementary searches to mitigate hallucinations.

03
Provenance Tracking

Logging evidence attributes (relevance scores, paths, URLs) to generate citation markers that link directly back to verified grounding sources.

04
Concurrent Computing

Using `asyncio` and `aiohttp` to parallelize multi-source web scraping and vector query executions, reducing search latencies under heavy query loads.

Education

2023 - 2027

Bachelor of Technology — Artificial Intelligence

Expected 2027
Alipurduar Government Engineering and Management College, West Bengal

Currently in my 3rd year (6th Semester). Studying core principles of deep learning architectures, classical optimization methods, and parallel computing infrastructures.

Relevant Coursework
Machine Learning & Deep Learning
Natural Language Processing
Neural Networks & Computer Vision
Probability & Mathematical Statistics
Data Structures & Algorithms (DSA)
Big Data Analytics & Databases (DBMS)
Technical Profile

Skills Inventory

Python C · C++ · Java
TensorFlow PyTorch · Keras · Scikit-learn
LangGraph ChromaDB · FAISS · LangChain
BERT spaCy · NLTK · Hugging Face
Pandas NumPy · Matplotlib · Seaborn
MySQL MongoDB · Vector Indexing
Docker Git · Streamlit · Linux CLI
AWS Google Cloud · MS Azure
Featured Systems

Flagship Development

Stateful RAG Agent

ARIA: Autonomous Research Assistant

A 5-stage agentic RAG pipeline built with LangGraph. Instead of performing single-pass vector queries, ARIA plans query structures, retrieves text concurrently from multiple databases, evaluates claims, runs self-critique loops, and compiles a PDF report. Read the Installation Guide → for macOS & mobile setup.

Orchestrator LangGraph
Vector Store ChromaDB
Network Layer aiohttp / asyncio
Export Engine ReportLab PDF
Verification Rate 11/11 tests pass
Launch Demo Source Code
Download for Windows (Download → Extract → Double-click run_aria.bat)
Modular RAG Pipeline

RAGPro: Modular Document Indexing

A high-performance modular RAG pipeline focused on vector search indexing. Built to evaluate document chunking algorithms, test FAISS vector similarity search speeds, and benchmark response generation using OpenRouter LLM gateways.

Framework LangChain
Index Engine FAISS
Embeddings Hugging Face (BERT)
LLM Router OpenRouter
License Type MIT License
Let’s Collaborate

Interested in research collaboration or testing agent setups?

I am always open to discussing stateful RAG loops, claim verification critique systems, or custom LLM integrations.

Get In Touch
Connect

Contact Channels

Submit a message through the console interface on the right. Form validation checks will run client-side before sending.

contact_console.sh
Ready to send.