Multi-tenant RAG system
LiveAsk My Business
An embeddable AI chat widget for small businesses.
FastAPIPostgreSQL with RLSChromaDBRedis+3
Aryan Sharma. Sydney, Australia
I build AI systems that actually ship.
Bachelor of AI graduate, University of Technology Sydney. Building AI systems across RAG, computer vision, and reinforcement learning.
Selected work
Personal AI OS
Jebb
My personal AI operating system.
FastAPINext.js 15Supabasepgvector+4
Computer vision, vision-language models
Few-Shot Adaptation of CLIP (Capstone)
Reproduced and compared five state-of-the-art few-shot adaptation methods for CLIP: LP++, CoOp, PromptSRC, TaskRes, and PromptKD.
PyTorchCLIPConvNeXtViT
LLM safety and RAG
Legal Risk RAG (confidential)
Confidential technical contribution to an Australian legal-tech startup.
Node.jsFastifypgvectorAnthropic API
Computer vision
AutoLZ
A computer vision pipeline for detecting safe landing zones for autonomous drones.
YOLOv5OpenCV
Reinforcement learning
SonarMapper
A PPO-based reinforcement learning agent for autonomous underwater navigation in a simulated environment under partial observability.
Stable Baselines3Gymnasium
Ask Jebb
The concierge that answers questions about Aryan's work.
The portfolio edition of Jebb, Aryan's personal AI concierge. It answers questions about his work.
About
Bachelor of Artificial Intelligence graduate from UTS (2026, WAM 78.88). Builds applied AI systems end to end: a deployed multi-tenant RAG chat system, a personal AI assistant platform used daily, and a technical contribution to an Australian legal-tech startup. Currently exploring both industry roles and research directions in perception for autonomous systems.
Download Resume