AI Engineer & LLM Researcher
Building AI-native tools that actually ship. Obsessed with making large language models more useful, more controllable, and more open.
- π¬ Abliterix β Fully automated LLM abliteration framework. LoRA + Optuna TPE optimization, 135+ model configs, 9 peer-reviewed techniques (NeurIPS/ACL/ICLR). 0β1.5% refusal rate with 0.01 KL divergence.
- ποΈ OpenDB β AI-native database & long-term memory for AI agents. 93.6% on LongMemEval (#3 on leaderboard), zero embeddings, zero vector DBs β just SQLite FTS5. 12 MCP tools, works with every major agent framework.
- 𦬠OpenYak β Open-source local-first AI desktop app supporting 100+ models
- π§ LLM alignment research β abliteration, representation engineering & steering vectors
- π Vector search engines & RAG pipelines at scale
- π€ Multi-agent orchestration β built from scratch, no heavy frameworks
- π AI-native writing & knowledge systems
- π¬ 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
Full Stack
Infra
- π Honours BSc in Computer Science & Mathematics, University of Toronto (3.95/4.0)
- πΌ 10+ years in Databases, LLMs & AI Agent Systems