I work at the intersection of navigation research, sensor fusion, and real-time software systems. Currently focusing on resilient positioning algorithms for GNSS-denied environments, I combine academic research with Python, C++, and embedded systems development.

With a background in building calibration tools, data pipelines, and automation hardware, I focus on creating high-reliability systems that bridge physical sensors and software architectures.

My research interests center around Particle Filters, Extended/Unscented Kalman Filters, and Factor Graph Optimization techniques. I am particularly focused on dynamic calibration methods that can run directly on embedded hardware to correct MEMS IMU sensor errors on-the-fly.

Methodology

Core Principles

Validation-Driven

Focusing on physical truth. Verifying filter models with real-world sensor logs and hardware telemetry.

Embedded Efficiency

Optimizing matrix operations and estimation loops to run in real-time on low-power hardware.

Open & Reproducible

Maintaining modular structures, documented configurations, and clean dependencies for collaborative research.

Experience

Employment History

Data scientist & Software Developer (Part-time)

2026 – Present
Carbon Happy World

Developing green-tech software applications, carbon estimation models, and analytics platforms concurrent with PhD research.

Contractor (Automation Leader & Data scientist) (Part-time)

2023 – 2026
Proctor & Gamble UK

Led automation initiatives and built predictive data analytics pipelines, transitioning to part-time in 2024 to support PhD research.