AI Engineer & LLM Researcher
Building AI-native tools that actually ship. Obsessed with making large language models more useful, more controllable, and more open.
- 🔬 Abliterix — Fully automated LLM abliteration framework. LoRA + Optuna TPE optimization, 135+ model configs, 9 peer-reviewed techniques (NeurIPS/ACL/ICLR). 0–1.5% refusal rate with 0.01 KL divergence.
- 🗄️ OpenDB — AI-native database & long-term memory for AI agents. 93.6% on LongMemEval (#3 on leaderboard), zero embeddings, zero vector DBs — just SQLite FTS5. 12 MCP tools, works with every major agent framework.
- 🦬 OpenYak — Open-source local-first AI desktop app supporting 100+ models
- 🧠 LLM alignment research — abliteration, representation engineering & steering vectors
- 🔍 Vector search engines & RAG pipelines at scale
- 🤖 Multi-agent orchestration — built from scratch, no heavy frameworks
- 📝 AI-native writing & knowledge systems
- 🔬 Publishing fine-tuned & abliterated models on HuggingFace
Languages
AI/ML & Deep Learning
Research & Techniques
-5B21B6?style=flat){kind=icon}
LLM APIs & Inference
Vector Databases & Retrieval
System Design & Distributed Systems
-0288D1?style=flat){kind=icon}
-E6522C?style=flat&logo=prometheus&logoColor=white){kind=icon}
Full Stack
Infra
- 🎓 Honours BSc in Computer Science & Mathematics, University of Toronto (3.95/4.0)
- 💼 10+ years in Databases, LLMs & AI Agent Systems