Todd Wolven

Generative AI (LLMs, Diffusion Models), Efficient Inference & Quantization (W4A16/AWQ via llm-compressor, vLLM, multi-GPU serving), Model Fine-tuning & Alignment (incl. Chain-of-Thought), AI Safety & Security (Red Teaming, Vulnerability Assessment), Retrieval Augmented Generation (RAG), Agentic Systems, Open Source AI Development (Model Context Protocol), Deployment (Docker, AWS/Azure).