John Hodge
Research scientist and engineer working on ML for physical systems.
I build models and tools for hardware reliability, RF and electromagnetic systems, engineering design optimization, and infrastructure-scale decision-making. The common thread is physical systems: problems where the data is messy, the failure modes are real, and the model has to survive contact with engineering judgment, cost, and operational constraints.
See the projects Resume Get in touch
What I work on
Applied ML for hardware reliability
Repair recommendation, failure diagnosis, and high-precision decision systems built on noisy operational logs.
Physics-based engineering and simulation
Electromagnetics, phased arrays, RFID, and design trade studies across thermal, power, and RF.
Open-source tools for engineering decisions
Optimization packages, simulation, and reliability modeling for physical infrastructure.
Featured projects
All projects →Hardware diagnostics and repair recommendations
Industry workProduction ML decision systems that fuse server telemetry, logs, and repair history into calibrated, component-level repair recommendations for AWS EC2.
- Python
- PyTorch
- SageMaker
Agentic Phased Array Builder
An LLM agent that designs phased-array antennas end to end, driving electromagnetic solvers and array models through the Model Context Protocol.
- Python
- LLM agents
- MCP
EdgeFEM
An open-source C++20 finite-element electromagnetic solver for RF and mmWave: S-parameters and radiation patterns from 100 kHz to 110 GHz.
- C++20
- Python
- Eigen
My PhD work was on reconfigurable metasurfaces and generative deep learning for electromagnetic design. See the research, publications, and talks →
Beyond the work
Coffee, investing, reading, hiking and the outdoors, travel, and Duke basketball. I also build BeanBench, a specialty-coffee logging app for iOS.