Practical AI · Machine Learning · Research
I'm a technology lead working on large-scale machine-learning systems, including intelligent data matching, LLM-assisted workflows, embeddings, vector search, and the data platforms behind them.
My research explores anomaly detection in complex technical systems using physics-informed models, statistical methods, digital twins, and autoencoder neural networks.
I work across applied machine learning, intelligent data systems, and research focused on making AI useful in real-world environments.
Digital twins, statistical methods, and neural networks for detecting degradation from telemetry.
Entity resolution, embeddings, vector search, and relationship discovery.
Retrieval, agents, evaluation, and reliable local-first pipelines.
Visual inspection, tracking, counting, and analytics for physical environments.
Kimi K3 combines a sparse mixture of experts, linear attention, and depth-wise routing. Here is what its architecture changes for AI teams.
A practical method for detecting solar-panel anomalies by calibrating a two-diode digital twin from voltage, current, temperature, and irradiance telemetry.
I’m open to thoughtful conversations about practical AI, computer vision, research, speaking opportunities, and advisory collaborations.