Hackathon Portal
AI Tinkerers - San Francisco
Final round winners have been announced. View Results
Team

q_star_agent

Project Concept

One-man one-agent. Let’s go.

Entry

Status: Submitted

Last saved: February 21 at 4:37 PM PST

Team Roster

You must be registered for the event to view the team message board.

Quilee Simeon Team Lead RSVP Approved

Research Engineer (Neuro + AI) at MIT Office of Research Computing and Data (ORCD)
Designed and implemented the full hybrid routing architecture using the Cactus Compute SDK and FunctionGemma-270M-IT. Built the tool relevance ranking system, intent-scaled token budget, argument verification pipeline, and confidence-gated Gemini 2.0 Flash fallback via Google AI API. Conducted a fork analysis of all public hackathon submissions to benchmark community strategies and inform the final approach.
Quilee Simeon is a Research Engineer (Neuro + AI) at the MIT Office of Research Computing and Data (ORCD) in Cambridge, Massachusetts, United States. Quilee studied Brain and Cognitive Sciences, Computation & Cognition, and Neuroscience at the Massachusetts Institute of Technology (MIT). With five years of experience, Quilee is currently seeking full-time work, specifically looking for Founding Engineer roles, and can help with technical architecture. Quilee is open to introductions and prefers contact via email. Quilee's tinkerer role is Data Scientist.
Neuroscience, AI, machine learning, high-performance computing, Slurm, containerization, neural data pipelines, multimodal alignment, long-horizon modeling, microscopy hardware, optomechanics, bioinformatics, technical architecture, sparse training for large language models, founding engineers
Projects include end-to-end neural data pipelines for preprocessing and multimodal alignment using Python, Julia, and MATLAB; optimizing HPC workflows on Slurm with Docker/Singularity containers; and prototyping microscopy hardware and optomechanics using Onshape and Thorlabs. Additional work involves building Arduino-based behavioral rigs and conducting machine learning experiments, specifically focusing on sparse training for large language models (LLMs).