Rohith Shinoj Kumar
Software Engineer | Exploring Scalable Systems & ML
I'm a final-year Computer Science and Engineering student at the National Institute of Technology Karnataka. I’m passionate about building scalable systems at the intersection of software engineering and machine learning. With a strong foundation in Python, C++, and ML, I’ve worked on end-to-end projects across MLOps and full-stack development — turning ideas into deployable, impactful solutions. Always eager to learn, collaborate, and innovate. Let’s connect!
Work Experience
Centre for Development of Telematics (C-DOT)
Research Engineer (Incoming)
August 2025 — Present- Yet to join
Accenture Inc.
Software Development Engineering Intern
May 2024 — July 2024- Designed and implemented a production-ready pipeline for dynamic pricing using real customer analytics data. Applied Facebook Prophet for time-series based demand forecasting, and Bayesian A/B Testing for price optimizations.
- Built a full-stack application to deploy the solution in a real-time business environment — integrating a ReactJS frontend with Flask-based backend APIs to serve model predictions and automate pricing adjustments aligned with demand metrics. Focused on clean architecture, modularity, and performance to ensure scalability and maintainability across potential product lines.
Outside the Stack (OTS)
Member of Project Team - Remote
Feb 2024 — May 2024- Collaborated closely with the engineering team, under the guidance of Nalini Elkins, to optimize buffer utilization and reduce latency in a TLS forward and reverse proxy pair, enabling seamless secure connections between clients and servers with incompatible or deprecated SSL versions.
- Designed and implemented a logging system that flushes SSL session history and keylog data to memory-mapped JSON files, replacing the initial system logger. This improvement reduced read-write latency by approximately 20% and CPU utilization during peak loads by 8%, enhancing overall proxy performance and reliability.
Featured Projects
ChatWithPDF: PDF Chatbot with OCR
Multimodal PDF question-answering system that integrates LangChain with HuggingFace open-source models, together with OCR and Image recognition tp extract and interpret both text and visual information (graphs/charts/photos) from documents. THe final model is wrapped in a a simple Flask UI to allow user PDF upload and question
DeliverEats: An On-Campus Food Delivery System
Production-ready web application for online food ordering in campus, enabling customers to browse menus, place orders, and make secure payments with restaurants inside NITK with a dynamic, user-friendly interface. Implemented secure payment workflows via Razorpay API and encrypted user transactions.
PomoNet-v1: Pomegranate Crop Disease Identification
This project is a part of a funded joint initiative between NITK and Indian Council for Agricultural Research (ICAR). Trained on a highly limited ~500 images sourced directly from farms by ICAR, the model achieved a 97.7% accuracy on independant evaluation. The full training and inference pipeline was delivered to ICAR for integration into their mobile diagnostic tool to support real-time, field-level disease identification.