Jolie Abadir

Computer vision, robotics, and the neuroscience of how systems sense and act.

I build computer vision and robotics software, and I'm headed toward intelligent biomedical hardware: prosthetics and assistive robotics. Cognitive science and computer science at Columbia (Barnard College). Looking for a summer 2027 robotics or health-tech internship.

What I'm Up To

Building 3D objects with only voice and hand gestures.

Workshop

A personal fun project: talk and gesture to build things like rockets, the way Tony Stark talks to JARVIS. It starts from basic blocks like a cone, and the hard part is teaching the system what a more complex object is, like a nozzle, then composing it into a rocket. Parts are parametric components with typed connector ports, so the Builder agent never computes coordinates. An Owl agent then judges front, side, and top renders with Claude Vision, and a Mechanic agent corrects rotation, scale, and position using exact scene-graph geometry and OpenCV three-view triangulation, looping until it converges. No model in the system was trained on 3D data.

Research prototypeSole Developer
Next.jsReact Three FiberClaude APIOpenCVMediaPipe+2
Three 3D parts snapping together into a rocket
→

About

Since I was a kid I've been obsessed with how things work, whether that's a shoulder joint or a circuit board. At some point it stopped being a hobby and became the way I see everything. When I hit a problem, I see the system it lives in: what feeds it, what it's connected to, what breaks downstream.

The useful part is that systems repeat. A nervous system and an embedded device are solving the same problem: sense the world, move a signal, decide, act, and correct when the result is off. I learned that loop in my own body as a climber before I had words for it, then found it again in neuroscience, and again in sensors and motor control. That's why I study cognitive science and electrical engineering at the same time, and why I'm headed toward intelligent biomedical hardware, like prosthetics and assistive robotics, where the nervous system and the machine have to work as one system.

Education

Columbia University
Barnard College
BA Cognitive Science (Embodied Cognition), Minor in CS. Expected Dec 2027. Dean's List, Spring 2026.

CU Boulder
Online, concurrent · planned completion May 2028
Graduate coursework toward the MS in Electrical & Computer Engineering, Embedded Sensors and Motors pathway.

Looking For

  • A summer 2027 robotics or health-tech internship, ideally close to the hardware
  • Research conversations about climbing biomechanics, movement data, or attention
  • Climbers and researchers who want to help label video in the Dynalytix pilot

Coursework

Robotics Studio, Advanced Neuroscience Lab, Machine Intelligence, Natural Language Processing, Biological Image Computing (graduate level), UI Design, Data Structures

Graduate: Sensors and Sensor Circuit Design, Supervised Learning

Research & Writing

Senior Thesis, Cognitive Science

Mentor: Prof. Joshua Kramer · 2026 – 2027

Gaze-guided grasp prediction: a model that reads where a person is looking in egocentric video, predicts what they will reach for and how, and drives a simulated robot hand to pre-shape before the reach lands. Built on public gaze datasets, no new data collection, as a prototype for shared-control assistive grasping.

Context Management in an LLM Dev Workflow →

Machine Intelligence, Columbia. 133 build-log entries, three failure classes, a retrieval prototype.

Priority Map Dissociation in Autism and PTSD →

Philosophy of attention, Columbia. An architectural constraint on selection-for-action.

TH+ Cell Analysis →

Biological Image Computing (graduate level), Columbia. Cellpose pipeline with an honest failure analysis.

Athletics

Elite climber

10th at the North American Championships and 14th at the Pan American Championships in bouldering, 2026. Competed at national team trials for a spot on the World Cup team.

Snowboarding

3× USCSA All-American: three top-10 finishes at collegiate nationals, across rail jam and slopestyle.

Skills

Programming

Python, Java, JavaScript/TypeScript, SQL

Vision & ML

OpenCV, MediaPipe, TensorFlow, scikit-learn, Cellpose, scikit-image, Gymnasium (RL), multi-agent LLMs, Claude API

Neuroscience & Cognition

Neuroanatomy, neural decoding in Python, fluorescence image analysis

Web & Infra

React, Next.js, FastAPI, Supabase, Postgres, Docker, Railway, Modal, Git

Hardware

CAD (Fusion 360), Raspberry Pi

Spoken

English, Arabic (conversational), Mandarin (elementary)