I'm a Machine Learning Engineer at Meta in London. Kaggle Competition Master and Notebook Grandmaster (former #1 global notebook ranking). Google Developer Expert.

I'm an economist by education, and I moved into ML in 2017. Since then, I've worked on churn, fraud, recommendations, video super-resolution, chat-bots, and ads at scale across telecom, banking, medical AI, ride-hailing, and big tech.

• 🌐 Personal site: andlukyane.com — bio, blog, projects.
• 📚 ML notes (Obsidian vault): dswok.com
• 🎤 Talks & interviews: andlukyane.com/activities#featured-talks
• 📁 Older portfolio (2017-2021): erlemar.github.io — Kaggle kernels & pet projects.

• MiniMax Sparse Attention: Per-Group Block Selection for Cheap Million-Token Inference
• Testing MiniMax M3 on real tasks: repo refactor, screenshot debugging, and Spotify recommendations
• Book Review: 50 ML Projects to Understand LLMs
• Gamma-World: Simplex Agent Encoding and Hub Attention for Multi-Agent World Models
• Testing MiniMax M2.7 via API on three real ML and coding workflows