Hi, I'm Raghavendra
I'm a Software Engineer with over 2 years of experience working across web, mobile, and backend systems.
Over that time, I've had the chance to build and ship frontend
interfaces, mobile apps, and backend APIs — as well as design
cloud-based solutions that support real-world use cases. I love building things that are reliable, easy to use, and make a
difference for the people who use them.
Lately, I've been diving into AI-driven software development — exploring
agentic systems to understand how we can build
smarter, more adaptive applications.
Skills
Frontend
Cross Platform
Native Mobile Development
Backend
Databases
Enterprise
Cloud & Deployment Tools
AI / ML
My Journey
Software Engineer at Pequrel Technologies
Feb 2024 – Present
Worked on software solutions for an agri-tech startup focused on increasing farmer income using IoT-based crop drying and growing systems.Implemented web-based admin services, services to manage lifecycyle and features of microcontrollers and a Flutter-based mobile app for their customers.
Internship at Pequrel Technologies
Jan 2023 – May 2023
Built an admin dashboard to manage customers, products, and crop data. Designed solution for scheduling features to track crop drying sessions and farmer pickup times. Contributed to a React Native mobile app used by infrastructure operators to control and monitor deployed systems.
Academic Project at KLE Technological University
June 2022 – Dec 2022
Worked on a research project focused on AI-based medical image synthesis using Generative Adversarial Networks (GANs). The goal was to generate corresponding MRI scan t2 images from t1 brain MRI scan inputs and vice versa, using an unsupervised approach. We implemented CycleGAN to handle the image-to-image translation task without paired datasets. This involved reviewing multiple research papers and understanding statistical techniques to evaluate model outputs.
Academic Project at KLE Technological University
April 2021 – May 2022
Worked on a research project focused on AI-based Talking Face Generation (TFG), focusing on generating realistic head and facial movements synchronized with speech input. We explored state-of-the-art methods including Pix2Pix, CycleGAN, U-Net, and contrastive learning frameworks. Our work involved mapping speech features to facial expressions, incorporating concepts like facial action units and key point tracking. We studied related literature and conducted domain analysis on emotion modeling, temporal alignment, and visual fidelity challenges in speech-driven facial animation.