10
3
United States
8 years of experience
As an entrepreneur, I brought godel.space to life, combining my passion for innovation with practical execution. As an angel investor, I focus on emerging tech AI and space startups, fostering growth and development in cutting-edge fields. In my role as Treasurer of the IITGAA, I am actively involved in alumni relations and community engagement, strengthening the bonds within our network. A space enthusiast and humanitarian, I balance a demanding career with family life, constantly seeking self-discovery, self-sufficiency, and peace. Living in the Pacific Northwest, I am an avid lover of its natural resources and enjoy exploring the region's stunning beauty.
We're Team TerraSentinels part of MindsDB hackathon , on a mission to revolutionize land use monitoring with AI and geospatial data! Our project: Intelligent Land Use Monitoring Agent, aims to detect unauthorized land use, deforestation, and urban expansion in real-time by analyzing satellite images and large-scale geospatial datasets. We plan to use tech like MindsDB, Google Earth Engine, and TensorFlow, all wrapped in a sleek web interface with Flask. If you're passionate about AI, geospatial data, or just love tackling big challenges with a positive, can-do attitude, we’d love to have you on board!
SafeEdge is an AI-driven content moderation solution designed specifically for educational platforms. Leveraging advanced AI models, our tool operates entirely offline on edge devices such as tablets, laptops, and IoT devices, ensuring robust performance even in environments with limited or no internet access. The architecture of SafeEdge consists of several key components: Synthetic Data Generation: We use OpenAI's Meta-Llama-3.1-70B-Instruct-Turbo model to generate synthetic training data tailored to specific content moderation categories such as spam, inappropriate content, and misleading information. Fine-Tuned Model: The generated data is used to fine-tune the Phi-3-mini-4k-instruct model. This fine-tuned model is lightweight, optimized for edge devices, and includes specialized LoRA adapters for efficient inference. Edge Deployment: The fine-tuned model is deployed locally on devices using a Streamlit-based application. This application is designed to work entirely offline, providing real-time text categorization and content filtering without relying on external APIs or cloud services. Privacy and Security: By processing all data locally, SafeEdge ensures that user information remains private and secure. The architecture is robust, cost-effective, and highly customizable, allowing it to adapt to various educational environments and needs. This combination of advanced AI, local deployment, and a focus on privacy makes SafeEdge an ideal solution for creating safe, secure, and inclusive online learning environments globally.
Agent Armada is an AI multi-agent system designed to enhance search and rescue operations during natural disasters. By utilizing a Large Language Model (LLM) as a user-friendly interface, it enables dynamic interaction between human operators and a swarm of autonomous agents, allowing for rapid and efficient searches in challenging terrains while minimizing risks to personnel. The LLM interprets user commands and orchestrates agent activities in real time, streamlining communication and enhancing situational awareness, which improves response times and operational effectiveness compared to traditional methods. Beyond disaster response, Agent Armada has applications in military reconnaissance, environmental monitoring, and other critical scenarios. Its strength lies in operating without pre-programmed logic, as the LLM adapts its actions based on real-time information and human input. The framework allows the LLM to interact with 3D geospatial environments through a swarm of agents, enhancing decision-making in complex terrains. This flexibility enables Agent Armada to tackle a wide range of challenges, from monitoring environmental changes in national parks to intelligence gathering in unfamiliar areas. By continuously learning from operator interactions and environmental feedback, it improves its performance and adaptability, providing timely support in diverse, high-stakes situations and enhancing operational efficiency and safety across various fields.