Education
Machine learning engineering · Electrical engineering
Building measured, reliable machine learning systems.
I bring an electrical engineering foundation to practical machine learning work, with an emphasis on systems that can be evaluated, explained, and operated.
Exploring machine learning engineering opportunities.
Certification
AWS Machine Learning Engineer credential
Production ML implementation and operationalization.Focus
Applied ML systems
Evaluation, retrieval workflows, and production-minded engineering.Selected work
ML projects presented as complete engineering stories.
The flagship case studies will pair architecture and implementation decisions with measured evaluation. Results will be published only after they are reproduced and verified.
Flagship case studyCase study in preparation
Bookmark ML System
A unified case study for Bookmark Smart and Bookmark Tools: a browser workflow paired with utilities for preparing, reviewing, and modeling bookmark data.
- Local, lightweight bookmark classification with rule-assisted handling.
- Dataset preparation and review workflow for training-ready examples.
- Evaluation results and operational evidence will be added once verified.
Flagship case studyCase study in preparation
Local RAG Toolkit
A local-first retrieval-augmented generation toolkit for ingesting documents and asking grounded questions with traceable sources.
- Document ingestion and configurable retrieval pipeline.
- Private, local workflow designed around source-backed answers.
- Retrieval, citation, and latency evaluation will be published with verified results.
Supporting projectSupporting engineering project
Metadata Multitool
A local-first image metadata utility focused on controlled cleanup and privacy-conscious file preparation.
- Local processing for image metadata workflows.
- Desktop and command-line interfaces.
- Batch cleanup, dry-run review, and reversible workflows for safer file handling.
Side projectVersion 2 in development
Data Continuum
An incremental systems game built around machine-learning metaphors, now being rebuilt as a dedicated experience separate from the professional portfolio.
- Interactive systems design and progression balancing.
- Canvas-based visualization and adaptive performance work.
- Available as a separate experience on this site.
How I work
From signal to system.
A practical engineering approach for work that has to perform outside a notebook.
- 01
Practical ML workflows
Framing the problem, preparing usable data, selecting a grounded baseline, and making evaluation part of the product—not an afterthought.
- 02
Retrieval and evaluation
Building retrieval workflows with traceable sources and explicit plans for measuring relevance, answer quality, latency, and failure modes.
- 03
Systems-minded engineering
Applying an electrical engineering foundation to performance, observability, reliability, and the practical constraints around an ML system.
About
Engineering judgment beyond the model.
My electrical engineering background shapes how I approach machine learning: define the signal, understand the constraints, measure the system, and make tradeoffs explicit.
This portfolio is being rebuilt around complete technical case studies. Each one will document the problem, data, architecture, evaluation, results, limitations, and next steps without relying on unverified claims.
Resume draft
The accessible HTML draft is available now. Employment, education, credential details, and the final PDF remain pending factual review.
Review resume draftContact
Let’s talk about useful ML systems.
I’m interested in machine learning engineering work where evaluation, software quality, and real-world reliability matter.