A little bit about me

my day job

software engineer, data scientist, statistician

I'm a software engineer on the IBM Watson team building tooling to help developers train and evaluate ML models. I develop applications using Node.js, React, Python and Java.

I've also worked as a data scientist, a data analyst and a statistics consultant. A common theme across all these roles has been data, particularly on how to use and visualize it to help users make more informed decisions.

What I Bring

  • Full-Stack Development: Hands-on experience across backend, frontend, APIs, and data systems. Comfortable working from concept to delivery, including prototypes, integration, and production deployment.
  • API & Data Architecture: Special focus on data products and developer experience—designing APIs that are intuitive, consistent, and usable. Includes metadata modeling, schema design, governance-aware architecture, and spatial data APIs.
  • Technical Leadership & Delivery: Experience as a tech lead, scrum lead, and project manager—guiding teams through planning, prioritization, estimation, and delivery. Skilled at balancing product goals, technical debt, and team capacity to deliver sustainably and strategically.
  • Cross-Disciplinary Collaboration: Worked directly with clients and domain experts in healthcare, tourism, infrastructure, and utilities. Skilled at translating requirements into technical decisions and ensuring stakeholders are part of the process.
  • User-Centered Engineering: Engineering work grounded in usability, maintainability, and clarity. I build systems that are technically sound and intuitive to work with—because the best systems are the ones people can actually use and evolve.

Portfolio

Selected projects that bring together data modeling, system design, and user-centered engineering.

🧠 Data Modeling

  • Hybrid Healthcare + AI Data Model (IBM Research): Designed a flexible and governance-compliant data model for AI/ML in clinical settings—balancing rigid healthcare standards with the flexibility of discovery-based workflows.
  • Spatial Data API & Ontology Design: Developed API models and ontology structures for spatial data standards as part of a research thesis integrating GIS and domain-specific schemas.

🛠 System Design

  • Observability Framework for Population Health: Created a modular, traceable architecture supporting insight, monitoring, and planning across diverse health data sources.
  • Fleet Health System: Designed predictive modeling pipelines and observability tooling to move from reactive to proactive automotive system maintenance.

🎯 Usability & User-Centered Design

  • Developer Tooling for AI Workflows: Built front-end tools and API interactions to help developers explore, train, and evaluate machine learning models more effectively.
  • Interview-Based Data Model Design: Conducted interviews with stakeholders across tourism, infrastructure, and healthcare to model data in ways that align with how people actually describe and use it.

Observability & Monitoring Systems

From insight to foresight—designing systems that help us see clearly, act wisely, and prepare for what’s next.

I build observability and monitoring systems across domains—from healthcare and automotive fleets to IT infrastructure and AI/ML systems. My approach integrates monitoring with forecasting—so we’re not just tracking the health of systems, we’re anticipating future needs, risks, and opportunities.

Where I’ve Worked:

  • Population Health Observability (IBM Research): Hybrid data models that support both regulated healthcare data governance and AI/ML discovery—enabling insight, traceability, and proactive planning.
  • Fleet Health Observability: Predictive modeling and performance monitoring for automotive systems—helping organizations move from reactive maintenance to foresight-driven operational decisions.
  • IT Systems Health (IBM AIOps + Instana): Observability tools that surface meaningful signals across distributed systems—integrating anomaly detection, forecasting, and root cause analysis for reliability and resilience.
  • Demand Forecasting Systems: Statistical modeling and data analysis for predicting resource needs, operational demand, and system load—whether for healthcare, supply chains, infrastructure, or transportation.