Work
A selected record of systems I tested and technical work I co-authored. Not a catalogue of every role or repository.
Independent investigations
Questions I tested with working systems, evaluations, and public methods.
A smaller model with better structure
In 35 head-to-head enterprise retrieval tests, Llama 3.1 8B with a knowledge graph beat Llama 3.3 70B on its own: a 55% higher core score, 13x lower input-token cost, 3x lower latency, and a verifiable tool-call chain.
Evaluation and technical articleLocal AI and intelligent scaffolding
A hands-on experiment in running a smaller local model inside explicit agent boundaries, observable workflows, and independent controls.
Systems experiment and technical article
Public technical work
Selected collaborative work published during my time in industry.
Human review for industrial predictive maintenance
Co-authored AWS technical work connecting anomaly detection, human review, dataset improvement, and model retraining for industrial equipment.
Co-authored technical work at AWSIndustrial asset monitoring with IoT and machine learning
Co-authored two-part AWS architecture for connecting industrial telemetry, asset models, monitoring, machine-learning training, and scheduled inference.
Co-authored two-part technical work at AWS