Michael Sugimura
ML Engineer
About Michael
Neural net and GPU enthusiast
ML Engineer with a decade of experience training — and sometimes coercing — machine learning models to solve industry problems in computer vision, NLP, and recommendation systems. Motivated by solving hard, high-impact problems with elegant ML solutions that scale.
Michael's Insights
Written contributions and insights from Michael.
Week 0 Nvidia DGX Spark Experiments
Week 0 experiments with NVIDIA DGX Spark - benchmarking Llama 4 generation, setting up DeepSeek OCR, and training LoRA adapters on 70B models with 128GB unified memory. Read more...
We Gave AI Agents Twitter and They Actually Got More Done
Research showing AI agents become more efficient when given access to social media and journaling tools, with 15-40% cost reductions on challenging problems through collaborative workflows. Read more...
Experimenting with GraphRAG: Adding Knowledge Graphs to RAG Pipelines
Blending knowledge graphs with RAG pipelines unlocks richer, scalable insights—bridging the gap between granular retrieval and holistic understanding. Read more...
Self-Learning LLM Agents: A Fractal Approach to Domain-Specific Knowledge
Exploring how agents can autonomously build and evolve their own domain expertise—scaling from generic LLMs to self-learning, specialized assistants. Read more...
Team Spirit Matters: How Collaborative Context Boosts Multi-Agent LLM Performance
Adding social accountability to multi-agent workflows boosts the depth, coherence, and empathy of LLM responses—mirroring real-world teamwork dynamics. Read more...