Hi, I'm Diwakar Ravichandran

I graduated with a Master's degree in Robotics from the University of California, Riverside, where I specialized in computer vision, SLAM (Simultaneous Localization and Mapping), and autonomous systems. My thesis, Celesta, is a fully differentiable optimization framework that integrates distributed bundle adjustment with Leiden-based graph partitioning for scalable, GPU-accelerated visual SLAM using NVIDIA Thrust.

Previously, I worked as a Data Scientist at Jio Platforms Ltd., where I developed and shipped computer vision solutions for drone-based tower reconstruction using SLAM. I contributed to video analytics for surveillance and visual document understanding, delivering production-ready pipelines from prototype to deployment.

Lately I've gone deep on the GPU layer underneath perception and ML systems — writing custom CUDA kernels for LLM inference (fused attention, KV-cache compression, quantized GEMM on Llama 3.1 8B) and profiling every optimization with Nsight Compute. My toolkit spans C++, Python, CUDA, and ROS across NVIDIA platforms from datacenter GPUs to Jetson edge.

I care about writing maintainable, performant code and bringing research ideas into deployed systems — and I'm always chasing the next hard problem in robotics, perception, and GPU computing.