Amit Dutta portrait
👋

Hello, I'm Amit Dutta, an MLOps Engineer with 4 years of experience. I build scalable ML pipelines and full-stack applications using React, React Native, and Java Spring Boot. I'm currently pursuing a Ph.D. in Computer Science at the University of Nevada, Reno, focusing on adaptive learning systems.

About me

I'm currently pursuing a PhD in Computer Science at the University of Nevada, Reno, where my research focuses on adaptive learning systems combining machine learning and evolutionary computing. With over 4 years of experience in software development, I specialize in building scalable MLOps pipelines, modern user interfaces with React and React Native, and robust backend systems using Java Spring Boot.

Outside of my research and engineering work, I enjoy exploring new technologies and occasionally contributing to open-source tools. I’m always learning—currently diving deeper into cloud-native MLOps practices, real-time data systems, and scaling ML workflows in production.

My projects

NAT: Neural Adaptive Trainer

An adaptive system that uses a neural network to personalize training by predicting performance and targeting learner weaknesses.

  • Unity
  • Neural Network
  • ML
  • C#

RAFT: Rule-Adaptive Feedback Trainer

Implemented a rule-based system that adjusts scenario difficulty based on student performance in maritime navigation training.

  • Unity
  • Rule-Based System
  • Python

Sharebike

A white-label bike-sharing app developed using React Native, Firebase, Stripe, and CodePush. Integrated CI/CD with Fastlane and CircleCI.

  • React Native
  • Firebase
  • Stripe
  • CI/CD

ERP Management App

A full-featured ERP system for managing HR, inventory, and sales. Built with React Native and Redux, available on Android and iOS.

  • React Native
  • Redux
  • ERP
  • Mobile

Upay Website

Responsive website for Upay built using Next.js and Tailwind. Showcases services, charges, and features based on Figma designs.

  • Next.js
  • Tailwind
  • React
  • Web

Reinforcement Learning for Trading

Developed a PPO-based reinforcement learning agent in a custom OpenAI Gym environment to simulate stock trading decisions.

  • Python
  • PPO
  • Reinforcement Learning
  • Gym

Bangla Grapheme Prediction

Built a handwriting recognition model using ResNet-50 and PyTorch for Bengali graphemes. Submitted to a Kaggle competition.

  • PyTorch
  • ResNet
  • Computer Vision
  • Kaggle

Food Recommendation System

Used KNN to build a simple food recommendation engine based on user preferences.

  • Python
  • KNN
  • Machine Learning

My skills

My experience

Contact me

Please contact me directly at [email protected] or through this form.