Robotics Engineer & Computer Vision Researcher
Graduated with a Master's degree in Robotics from University of California, Riverside. Specializing in SLAM, computer vision, and autonomous systems. Experienced in shipping production code in industry and research—from drone-based 3D reconstruction to real-time perception pipelines. Passionate about robotics and AI.
I graduated with a Master's degree in Robotics from 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 with Jio Platforms Ltd., where I developed and shipped computer vision solutions for drone-based tower reconstruction using SLAM technology. I contributed to video analytics for surveillance and visual document understanding, delivering production-ready pipelines from prototype to deployment.
My technical expertise includes C++, Python, MATLAB, and ROS (Robot Operating System), with hands-on experience in GPU programming (CUDA) and NVIDIA platforms. I focus on writing maintainable, performant code and bringing research ideas to deployed systems. I am passionate about advancing robotics and AI for real-world applications.
Robotics Degree
Years Experience
Research Projects
A project demo to try out Celesta. Explore the repository for implementation details and usage.
Helper repository to visualize dense 3D reconstructions from SLAM and structure-from-motion pipelines.
Vehicle-to-vehicle communication systems for intelligent collaborative driving. Autonomous vehicles in CARLA simulation with multi-agent coordination.
A fun project implementing a simple neural network in CUDA for MNIST digit classification, written in C++ with GPU acceleration.
Bayesian drift modeling and analysis for semiconductor applications. Jupyter-based workflows for inference and visualization.
GPU-accelerated bundle adjustment for structure-from-motion and SLAM using CUDA for real-time optimization.
A fully differentiable optimization framework that integrates Distributed Accelerated Bundle Adjustment (DABA) with the Leiden algorithm for improved graph partitioning in visual SLAM. Implemented with NVIDIA Thrust, Celesta achieves scalable, GPU-accelerated bundle adjustment with balanced workloads and better convergence than Louvain-based partitioning. Master's thesis, UC Riverside.
Download thesis (PDF)
C++
ROS
MATLAB ®
PyTorch
CUDA ®
OpenCV
TensorFlow
I'm always interested in new opportunities and exciting projects. Whether you have a question or just want to say hi, feel free to reach out.