“Don’t aim for the goal, aim to become the person who can achieve it easily.”
你好!, I'm Brik H. Meza
I am an incoming MSc CS student at McGill University. I co-founded Outliers, an AI and software consultancy for SMEs, and NONHUMAN, Peru's first student-led Embodied AI lab.
Previously, I interned at BSH Home Appliance and worked as an AI Research Engineer at EsSalud, where I led health-AI projects. I received my Bachelor's degree in Mechatronics Engineering from PUCP in 2025.
I am interested in the intersection of artificial intelligence and autonomous physical systems. I am excited about startups and the future of humanity and robots in space.
Hugging Face
Selected Projects
My nindo to become a full stack robotics engineer.
Automatic Package Sorting System
Modular mechatronic system for automated package classification using barcode detection and independent sorting modules. Designed to reduce space requirements while maintaining scalability.
MANTRA
The NONHUMAN team built an ALOHA-style bimanual manipulator using Piper arms, achieving a system 4x cheaper than Stanford's original ALOHA. I led the mechanical design and developed the teleoperation and data-collection stack. The team collected over 2,000 pick-and-place episodes (dataset available on HuggingFace) to fine-tune and test the π0.5 model.
Autonomous Dump Pocket Cleaning Using Imitation Learning
Paper submitted to the World Mining Congress 2026. Experimental testbed and benchmark for evaluating imitation learning architectures on autonomous dump pocket cleaning. Benchmarks four IL architectures (ACT, Diffusion Policy, π0.5 model, and SmolVLA) using a SO-ARM100 platform with granular bentonite material.
Nutribot: AI Chatbot for Preventive Nutrition Education
Multimodal AI chatbot deployed on WhatsApp for preventive nutritional education at EsSalud Peru. Impacted 200+ users, achieving a SUS score of 78.9/100 and 85% improvement in diet adherence.
MediVoz: Smart Transcription for Medical Consultations
AI voice agents that convert real-time medical consultations to structured clinical records. Engineered the full-stack demo pilot; reduced clinical note-taking time by 70%.