🔭 I’m currently working on: Engineering AI-powered RAG chatbots and agentic NLP pipelines to improve research efficiency.
👯 I’m looking to collaborate on: Open-source projects focused on deep learning inference optimization and high-performance model deployment.
🤝 I’m looking to: Mastering advanced multi-agent orchestration and staying ahead of the curve in 2026's LLM research trends.
🌱 I’m currently learning: Advanced local-first RAG techniques, dense vector indexing with FAISS, and scaling workflows in Slurm-based HPC environments.
💬 Ask me about: Model pruning, quantization, NLP preprocessing pipelines, and deploying machine learning on embedded ARM systems.
⚡ Fun fact: I have a knack for speed—I've previously improved model performance by 2-4x through custom quantization and graph transformations.