ML engineer focused on practical, production-ready systems.
I spend most days turning messy ML ideas into tools people can actually
use, not just demo once and forget.
How I like to work
I usually sit in the middle of product, data, and engineering. The best
projects for me start a little messy, get shaped with the team, and end
up as something useful in day-to-day work.
A lot of my work has been in mining and heavy industry, but the same
rules keep showing up everywhere: understand the workflow, build with
constraints, ship fast, and keep listening to users.
Outside project delivery, I like writing practical ML notes and helping
teams get better at modern AI without the hype spiral.
• Designing, experimenting, building, and deploying production-ready machine learning models in Python using Amazon SageMaker.
• Engineering and maintaining data pipelines for ingestion, preprocessing, and feature engineering with AWS services including S3 and Lambda.
• Working with domain experts and product owners to translate mining and processing needs into clear ML problem statements with measurable success criteria.
• Applying MLOps practices including CI/CD workflows, automated retraining, and monitoring for model performance drift.
• Running analysis and experimentation to validate hypotheses and improve recommendation and predictive models for operational efficiency.
• Supporting live models in mineral processing environments with engineers and analysts, troubleshooting issues and continuously improving performance.
