Joshua Chilukuri
Passionate about the intersection between technology, business, and public service, and creating solutions to solve global issues.
Hey there! I'm Joshua Chilukuri...
... a student whose deeply passionate about computer systems, AI, economics, and public service. My journey started at Apex High's Academy of Information Technology (AOIT) where I learnt basic technology skills (Microsoft 365 Certification, Databases) while leading initiatives in finance and service outside of the classroom. As I gradually discovered an excitement for data science, I hunted down free courses online to learn how to train analytical algorithms. Through Andrew Ng's Machine learning specialization, I realized machine learning's applications extended far beyond basic financial analytics.
Driven to develop my understanding of AI, ethics, and technology, I applied to the North Carolina School of Science and Mathematics to pursue greater educational opportunities. Today, I serve as the school's Student Senate President, an Editor-in-Chief for the Broad Street Scientific Journal, Secretary on the UNC Association of Student Gov. Budget & Finance Committee, Captain of our Machine Learning Group, and Co-President for our Key Club chapter.
Today, I'm deeply interested in interactive AI systems (vision technology), and how the intersection between electrical engineering and computer science allows advanced human-computer interaction. I'm additionally curious to explore how these systems can be implemented ethically and safely for the future. I'm also continuing to build my understanding of computer information systems, and am a Co-Founder of Hiant Development (hiant.tech) with my partner Trevor Bedson, where we build full-stack member management apps for large-scale organizations.
Projects Gallery
AVISION (In-Progress)
Currently buildling touch-activated AI glasses interface, designed to access custom APIs for blind navigation, data extraction, and object memorization.
Indoor-RFDETR
Trained using a high performance computing cluster, Indoor-RFDETR is a fine-tuned variant of the Roboflow Detection Transformer architecture for identifying key indoor objects (staircases, doorways, furniture, etc) to enhance blind navigation when implemented in smart glasses designs.
Voice-to-3D Object Generation Engine
Research project with Duke University's I^3T Lab -> Building methods for automated, real-time content generation in Mixed Reality (XR) environments. Awarded Best Paper at Augmented Interaction Workshop, IEEE ISMAR.
SightLine
AI-Glasses for the visually impaired. Leverages monocular metric depth estimation, YOLOv8 object detection, and image streaming to produce contextual system prompts for a cloud-hosted LLM, allowing specific, depth-informed navigation capabilities. Intel Global AI Award 2025
North Carolina TSA App
Serving 800k backend server requests, and downloaded by ~2k conference attendees, the North Carolina TSA App managed event data, notifications, and provided information tools for one of North Carolina's largest career technical service organizations (9k+ members).
Predicting U.S Food Insecurity: An Empirical Assessment of ML Approaches and Sociodemographic Predictors
Independent research, evaluating XGBoost, Random Forest, Neural Networks, and Google TabNet as predictive models for classifying food deserts using publicly available census data.
Ketchup
A mobile app designed for integration in elementary/middle schools, leveraging LLM's, PDF document uploads, and forum functionalities, to create a modern tool for teachers to support students catching up on absent work.
ARES-M Weather Sensor
ARES is a remote autonomous sensor suite, designed for deployment on Mars, monitoring temperature, humidity, seismic activity, UV/IR, and soil moisture in real time.
Publications/Articles
Current Learning Goals (2025)
Artifical Intelligence Engineering
Specifically focused on computer vision and natural language processing, and their applications in embedded systems (e.g Smart Glasses) on resource constrained devices. Also exploring the use of high-performance GPU compute for large-scale workloads in LLM fine-tuning/post-training and CV model training.
Augmented/Virtual Reality (AR/VR)
Applications of generative AI in augmented/virtual reality contexts for enhancing everyday interactions and advancing technology productively. Particularly interested in content generation methods, and object detection applications in AR interfaces. Also examining how these systems can be used in research towards AR/XR security systems.
Scalable Software Engineering
Learning backend systems (currently starting with a PostgreSQL and GoLang tech stack) and studying scalable software deployments via Docker/Kubernetes. Continuing to advance skills in web/mobile based frontend engineering and deploy impactful software tools through my work at Hiant.