Background:
I am an AI Researcher and Computer Vision Specialist with a robust academic and professional background in machine learning, robotics, and artificial intelligence. My expertise spans Scene Understanding, Depth estimation, 3D reconstruction, and neural radiance fields (NeRFs).
Expertise:
I specialize in training machine learning models, including large language models (LLMs), for scene understanding and visual localization. Proficient in robotics frameworks like ROS, I focus on motion planning, trajectory control, and system integration. My experience includes deploying optimized AI solutions on edge devices like NVIDIA Jetson using TensorRT and CUDA, delivering high-performance, real-time applications.
Applications:
I have developed pipelines for feature matching, image retrieval, and pose estimation, contributing to projects in 3D mapping, SLAM, and autonomous systems. My work bridges cutting-edge AI research with real-world applications, tackling challenges like obstacle avoidance and kinodynamic planning.
Skills:
Fluent in Python, C++, and MATLAB, I possess a strong foundation in probability, optimization, and linear algebra. My expertise includes CNNs, Transformers, and advanced deep learning techniques, supported by tools like Pytorch, OpenCV, Docker, and TensorRT to deliver innovative AI-driven solutions.