MACHINE LEARNING · DATA · MLOPS

Building ML systems
that go beyond the notebook.

I build practical machine-learning solutions with a focus on the engineering required to move models from experimentation into reliable, deployable systems.

View my work ↓ GitHub ↗
Focus ML Engineering & MLOps
Stack Python · AWS · MLflow · BentoML
production_ml_system architecture
END-TO-END PIPELINE
01 GitHub Source
→
02 CI / CD Automation
→
03 MLflow Tracking
validation · registry · deployment
04 BentoML Serving
→
05 AWS ECR Container
→
06 API Inference
production architecture MODEL → PRODUCTION
MODEL
REGISTRY
REAL-TIME
INFERENCE
01
Experiment Track & evaluate
02
Validate Quality gates
03
Deploy Containerised serving
04
Monitor Production feedback

01 / FEATURED WORK

Production-minded
machine learning.

A practical end-to-end project designed to demonstrate what happens after a model has been trained.

MLOPS PROJECT 01
MODEL SYSTEM HOUSE PRICE PREDICTION
Python MLflow Feast Deepchecks BentoML AWS ECR

House Price Prediction

End-to-end MLOps pipeline

A production-style machine-learning workflow covering automated training, validation, experiment tracking, model registration, packaging, container deployment and inference.

CI/CD pipeline Automated
Model serving BentoML
Container registry AWS ECR
Explore project → View source ↗
↗

The project page will expose the architecture, pipeline stages, model lifecycle, monitoring and a live prediction interface connected to the deployed model API.

02 / CAPABILITIES

From model development
to production.

01
⌘

Machine Learning

Model development, evaluation, feature engineering and practical problem solving.

scikit-learn PyTorch TensorFlow
02
◫

MLOps

Automated workflows connecting experimentation, validation, registration and deployment.

MLflow GitHub Actions Deepchecks
03
◇

Model Serving

Packaging models into reproducible services and exposing them through inference APIs.

BentoML REST APIs Docker
04
⌁

Cloud & Data

Cloud infrastructure and data components supporting reliable machine-learning systems.

AWS Feast PostgreSQL

03 / ABOUT

Turning data science
into working systems.

My work sits at the intersection of data science, machine learning and software engineering.

I am particularly interested in the engineering layer around machine learning: reproducible pipelines, model lifecycle management, deployment, APIs and monitoring. The goal is not simply to build a model that works in an experiment, but to understand how that model becomes part of a dependable system.

BSc Applied Mathematics
& Computer Science
ML Applied machine
learning projects
MLOps Production-oriented
system design

04 / CONTACT

Let's build something
useful with data.

Get in touch → GitHub ↗