Lead Software Engineer, Moonshot LA
I build software that processes live data from smart glasses. It uses computer vision and eye tracking to learn what the wearer sees and estimate what they might do next.
Nicolas Buitrago builds AI systems that understand the real world.
Bogotá / Los Angeles / Remote
Lead Software Engineer working on multimodal AI and world models for smart glasses. Previously built recommendation, RAG, LLM, and production ML systems across hiring, NLP, and computer vision.
I like building AI software for everyday use. My work includes processing live sensor data, finding relevant information, and giving agents the context they need to do a task.
Current focus
Work
Machine Learning Engineer, Rolebot
Built Rolebot’s AI system from scratch, including recommendation models, RAG workflows, LLM integrations, BERT and Llama deployments, FastAPI services, Django and Laravel backends, and Tableau data pipelines.
Machine Learning Engineer, Millenium BPO
Deployed NLP and audio classification models with Python, TensorFlow, Flask, and Docker. Built monitoring and clustering workflows for production model drift and ticket-system analysis.
Systems
What I build
World models for smart glasses
I combine video, eye tracking, motion, audio, and location data to keep a record of the wearer's surroundings. The aim is to help the glasses recognize places, notice changes, and offer help as things happen.
Agent engineering
I work on how agents use tools, find information, and keep track of a task over time. I focus on what they remember, how much context they need, and how to test their results.
Writing
La Casualidad
Escribo para humanos y máquinas. Notes on AI, perception, systems, language, and the personal side of technical work.
Read on Substack