Debapriya Das — Senior AI Engineer & Full Stack Developer

Professional Summary

About Me

AI/ML enthusiast with industrial experience in generative AI, backend development, DevOps, and agentic AI development for 2+ years. Passionate about building scalable systems, exploring intelligent solutions, and working with impactful technologies.

At Kvell Dynamics, I serve as Project Lead driving backend architectures with 60+ REST API routers, high-throughput IoT headend ingestion layers, and event-driven microservices.

I actively build open-source AI tooling, including Nyaya-GPT (83+ stars on GitHub), an agentic legal AI using RAG + ReAct loops, and conduct novel research on Graph-based Variational Autoencoders for molecular structure generation.

📄 View Resume (PDF) 🖥️ Interactive Web CV ✍️ Dev.to Articles

📍

Location Pune, Maharashtra, India

🏢

Current Role Senior AI Engineer @ Kvell Dynamics

📞

Phone +91 6295747430

✉️

Email debapriyadas73@gmail.com

💼

Status Open to impactful roles 🟢

Career History

Work Experience

Senior AI Engineer (Full-Time) · Kvell Dynamics

Oct 2024 – Present

📍 Remote, South Africa

🏦 RMB — Rand Merchant Bank (Project Lead)

Leading the development and DevOps team of 10+ members.
Architecting GCP cloud architectures for high-efficiency CI/CD pipelines.

⚡ Fungi — Smart Utility Management Platform (Project Lead)

Architected and developed a large-scale FastAPI backend with 60+ REST API routers for sites, meters, customers, billing, tariffs, and anomaly detection.
Designed PostgreSQL data layer using SQLModel / SQLAlchemy with Alembic migrations and connection pooling.
Built billing rule execution engine, tariff calculation (block rate, time-of-use, demand charge), and payment processing integration.
Implemented Redis caching, RabbitMQ background processing, and event-driven architecture using FastStream.
Built headend ingestion layer for 4 meter systems (M2M, Landis & Gyr, Sigfox, Scigrow) with async batch processing, delta calculation, and device-type routing (electricity, water, gas).
Led legacy data migration — PostgreSQL normalization and PostgreSQL-to-InfluxDB time-series migration with validation pipelines.
Developed AWS Lambda functions, Cognito auth flows, and SES email services via boto3; implemented JWT + Casbin RBAC, Docker containerization, and CI/CD pipelines.

⚖️ Murphy’s Law AI — Legal AI

Built conversational AI interface using Chainlit, integrated LLM APIs, and developed file upload feature.
Implemented RAG pipeline and ETL using Weaviate vector database and LangChain.

Hackathon Intern · ANNAM.AI

May 2025 – Jul 2025

📍 Rupnagar, Punjab, India (AI CoE, Ministry of Education, Govt. of India)

Participated in a hackathon-based internship organized by ANNAM.AI, an AI Centre of Excellence of the Ministry of Education, Govt. of India.
Developed AI solutions for real-time agricultural challenges under mentorship from domain experts.

Full Stack Engineer (Freelance) · Nearhouse

Sept 2022 – Jun 2024

📍 Santiniketan, India · nearhouse.in ↗

Developed backend APIs with Express.js from scratch for production platform.
Designed MongoDB database schema and automated CI/CD pipeline from GitHub to AWS EC2 via GitHub Actions.

Backend Engineer (Freelance) · Lazer

Dec 2021 – Dec 2022

📍 Remote, India

Created scalable REST APIs using Express.js and managed MongoDB data storage and AWS CI/CD pipelines.

Core Competencies

Skills & Technologies

🤖 AI / ML & Agents

LLMs & RAG LangChain PyTorch TensorFlow Weaviate InfluxDB Chainlit Streamlit DeepSeek R1 Groq OpenCV Scikit-Learn

💻 Languages

Python JavaScript Node.js Dart / Flutter C / C++ Java SQL HTML / CSS

⚙️ Backend, Cloud & DevOps

FastAPI FastStream Express.js PostgreSQL MongoDB Redis RabbitMQ Docker AWS (EC2, Lambda, Cognito, SES) GCP CI/CD Pipelines Casbin RBAC

Curated from Resume

Verified Projects

Showcasing production-ready systems, verified open-source frameworks, and computer vision projects from my professional curriculum vitae.

⚖️

⭐ 83 Stars 🍴 18 Forks 🔥 Flagship

Nyaya-GPT

A RAG+ReAct based AI agent framework on the Indian Constitution and Bharatiya Nyaya Sanhita (BNS). Answers complex legal queries with verified citation grounding via Llama 3.1-70b and Groq in an iterative reasoning loop.

Python Groq Streamlit Llama 3.1-70b LangChain

🚀 Live Demo Source Code

💰

⭐ 3 Stars NLP

The Tech Buddy (TaxBuddy)

An end-to-end personalized AI chatbot and agentic RAG system for Indian TAX related Q&As. Powered by DeepSeek R1 and Llama 3 via Groq with low-latency contextual retrieval.

Python Groq Streamlit Llama-3.1 DeepSeek R1

🚀 Live Demo Source Code

⚡

Industrial Lead

Fungi — Smart Utility Management

Large-scale IoT & utility platform backend with 60+ REST API routers. Includes billing rule execution, 4-meter headend ingestion (electricity, water, gas), Redis caching, and RabbitMQ event streaming with FastStream.

FastAPI PostgreSQL FastStream RabbitMQ InfluxDB AWS Lambda

View Project Details

🐟

Computer Vision

Custom Zebra Fish Detection

Computer vision project detecting zebra fish behaviors. Extracted video frames using OpenCV, manually labeled the custom dataset, and fine-tuned YOLOv5 models for object tracking.

Python YOLOv5 OpenCV PyTorch

GitHub Profile

🏛️

Legal AI

Murphy's Law AI

Conversational legal AI platform featuring an interactive chat interface built in Chainlit with multi-document upload. Features an ETL pipeline and high-performance RAG using Weaviate vector DB and LangChain.

Python Chainlit Weaviate LangChain LLM APIs

View Architecture

🏡

Production Live

Nearhouse Platform

Commercial real-estate web platform. Developed scalable REST APIs from scratch with Express.js, MongoDB database schema, and automated AWS EC2 deployment using GitHub Actions CI/CD.

Node.js Express.js MongoDB AWS EC2 GitHub Actions

🌐 Visit nearhouse.in

Want to explore additional experimental repositories and code sandboxes?

Browse All 43+ Public Repositories on GitHub →

Academic Background

Education & Degrees

Major in Artificial Intelligence · IIT Ropar

2024 – 2025

Coursework: Python, Artificial Intelligence, Prompt Engineering, NumPy, Pandas.

M.Sc. in Computer Science · Visva-Bharati University

2022 – 2024

CGPA: 7.75 / 10.0

Coursework: Advanced Machine Learning, Image Processing, Data Mining, Distributed Systems, Parallel Algorithms, Approximation Algorithms, Advanced Software Engineering, Quantum Computation.

B.Sc. in Computer Science · Visva-Bharati University

2019 – 2022

CGPA: 7.85 / 10.0

Coursework: C Programming, Computer Architecture, Data Structures & Algorithms, Operating Systems, DBMS, Theory of Computation, Numerical Methods, Artificial Intelligence, Soft Computing, Computer Networks, Linux Programming.

Science & Writing

Research, Publications & Certifications

🧬

Research Project Mar 2023 – Jun 2024

Generation of de novo Molecular Structures using Graph-based Variational Autoencoders

DCSS, Siksha Bhavana, Visva-Bharati University, India

Developed a generative AI model from scratch for producing novel molecular structures from graph inputs using Graph Neural Networks (GNNs) and Variational Autoencoders (VAEs).

Developed a novel Graph-VAE architecture with edge-informed graph convolutions.
Introduced a quadratic O(n²) complexity reconstruction loss, replacing quartic O(n⁴) complexity.
Preprocessed and fine-tuned on ESOL & TOX21 datasets. Enhanced chemical validity from 32% to nearly 98%.

Python PyTorch DGL DGLLife RDKit NumPy

📚

Articles

Publications & Articles

A study on erratic mental status in a young human population in respect to mate choice (Dec 2023)
sciforum.net/paper/view/16541 ↗
Exploring Word Embedding Techniques Based on Count or Frequency (Jul 2024)
Published on LinkedIn. Covers One-Hot Encoding, Bag of Words, TF-IDF.
Exploring Text Preprocessing Techniques in Natural Language Processing (Jul 2024)
Published on LinkedIn. Foundational NLP preprocessing essentials.

🎖️

Verified

Certifications

Introduction to Machine Learning (2021)
Duke University, USA
Logistic regression, MLPs, CNNs, and NLP with PyTorch hands-on.
Applications of Python in Big Data, NLP, and Social Network Analysis (2020)
IEEE Kolkata Chapter
Workshop on Python applications in Big Data, NLP, and SNA.

Get In Touch

Let's Connect

Whether you want to discuss AI systems, RAG architectures, or job opportunities — feel free to reach out.