Projects

Engineering projects from NVIDIA, CMU, and personal exploration in ML/Robotics.

NVIDIA Maxine — SDK Infrastructure & Triton Integration

NVIDIA AI • June 2021–Present

Working on AI features for video conferencing in the Maxine team. Integrated Maxine SDK with Triton Inference Server for large-scale inference with efficient batch processing. Implemented 2D image registration algorithms using CUDA/C++. Managing SDK infrastructure including releases, testing, and performance optimization.

C++ CUDA TensorRT Triton Computer Vision

Realistic Scenario Generation in CARLA (Capstone)

CMU with Ridecell • Jan–Aug 2020

Implemented goal-conditioned imitation learning for modeling traffic agents using expert trajectories in bird's eye view. Used DeepLabV3+ with MobileNet for vehicle motion prediction. Developed 3D to 2D homography projection for generating ground truth bounding boxes and built multi-object tracker for BEV vehicle tracking.

Python Deep Learning CARLA Detectron2 Autonomous Driving

SLAM Implementation with AMCL & Visual Odometry

Carnegie Mellon University • Aug–Dec 2020

Implemented Adaptive Monte Carlo Localization (AMCL) in C++ with OpenMP, achieving 10Hz performance with 5000 particles. Built monocular camera tracking framework integrating classic visual odometry with DL-based image-scan alignment using GTSAM factor graphs, showing improved performance over pure VO.

C++ Python SLAM GTSAM OpenMP

Mobile Robot Localization & Obstacle Detection

Carnegie Robotics • Summer 2020

Formulated bundle adjustment problem in Ceres Solver for offline robot localization using AprilTags. Developed software pipeline for obstacle detection using UV disparity maps in C++ and ROS2, achieving real-time performance for mobile robot navigation.

C++ ROS2 Ceres Solver Computer Vision AprilTags

Image Synthesis with GANs and NeRF

CMU Course Project • Jan 2021–May 2021

Implemented various generative models including Poisson blending, DCGAN, CycleGAN, and StyleGAN using PyTorch. Explored Neural Style Transfer and used Neural Radiance Fields (NeRF) for super-resolution. Gained deep understanding of modern generative AI techniques.

PyTorch GANs NeRF Computer Vision Deep Learning

DARPA SubT Challenge & Point Cloud Registration

CMU Biorobotics Lab • Jan 2018–Aug 2019

Developed culinary skills evaluation using HMMs and integrated pose estimation algorithms with ROS data pipeline. Evaluated point cloud registration methods (ICP, GICP, GO-ICP) against proposed algorithms. Built multi-robot Gazebo simulation for DARPA Subterranean Challenge.

Python C++ ROS PCL Gazebo

Computational Photography Suite

CMU Course • March–May 2021

Implemented uncalibrated photometric stereo, depth from focus, and structured light triangulation. Developed white balancing, color correction, and tone mapping algorithms. Created depth estimation from light field images and used GDP for image reconstruction.

Python Computer Vision Image Processing 3D Reconstruction

Autonomous Mobile Robot Navigation Stack

Addverb Technologies • June 2017–Jan 2018

Started and led the autonomous robotics division. Developed complete navigation pipeline for Autonomous Mobile Robots (AMRs) using ROS Navigation Stack. Implemented lower-level motor controls in C++ and recruited team members for the new division.

C++ Python ROS Navigation Robotics

Computer Vision Fundamentals (Lead TA)

CMU Teaching • Fall 2020

Implemented variants of Lucas-Kanade tracking algorithms, homography estimation, and multiview 3D reconstruction from scratch. Served as Teaching Assistant and led the 3D reconstruction assignment module, helping students understand fundamental CV concepts.

Python Computer Vision 3D Reconstruction Teaching

6D Object Pose Estimation with RGBD

CMU Visual Learning • March–May 2021

Reviewed and implemented various 6D object pose estimation refinement techniques using RGBD input. Compared different approaches for accuracy and computational efficiency. Explored applications in robotic manipulation and augmented reality.

PyTorch 3D Vision RGBD Deep Learning