I build production AI for the industrial world.
I'm a full-stack AI engineer with a decade of experience delivering production-grade AI for the chemical, manufacturing and industrial automation sectors. Chemical engineer by training, I work across the whole stack: first-principles reactor models, neural networks and Gaussian processes, the MLOps and infrastructure that keep them running against live plants, the web apps operators actually use, and increasingly LLM-powered and agentic systems. Currently at Navigance in Munich, where models I own optimise chemical plants around the world.
- $50M+value generated from predictive ML across global factories
- −3%energy consumption on live chemical plants
- 20×R&D throughput through robotics and automation
- 796×speed-up from re-engineering one production solver
What I do
Modelling
Neural networks, Gaussian processes and first-principles models, often hybrids of all three, built on noisy, real-world data where a wrong prediction has a physical cost.
Software & MLOps
Typed, tested, reviewed codebases and the machinery around them: deployment, monitoring, retraining and health alerting. I lead engineering standards as well as write to them.
Apps & interfaces
Full-stack development of the optimisers, dashboards and calculators that operators and engineers use every day, taken from notebook analysis to CI-validated production in days.
LLMs & agents
Retrieval-grounded assistants that answer from live process data, and agentic pipelines that carry a bug report through to a reviewed pull request. Practical, evaluated, and in production.
Experience
- 2024 — now
Data Scientist / ML Engineer — Navigance, Munich
End-to-end AI product ownership at a 22-person SaaS company optimising chemical plants worldwide. Hybrid neural-network and first-principles reactor models for methanol, ammonia, maleic anhydride and syngas plants, extracting up to 3% in energy savings on live processes. I architected the MLOps stack (Airflow, InfluxDB, TypeScript/Node), consult international clients on AI initiatives, and built the LLM tooling: a process-expert assistant grounded in live plant data and an autonomous bug-report-to-pull-request agent pipeline.
- 2021 — 2024
Engineer, Data Science & DevOps — Roke, Manchester
Cloud-hosted ML delivered inside a rigorously tested CI/CD environment: NLP, clustering and Gaussian processes that let analysts work through billions of data points in minutes. Led the project team as SCRUM Master; Best Roke Project Team 2021 and 2022.
- 2021
Consultant Chemical Engineer — Koch Technology Solutions, Wilton
Developed the company-wide digitisation strategy for a $100M+/year technology value stream, and architected the full-stack process automation that cut design-time-to-insight by 90%.
- 2018 — 2021
Senior Research Data Scientist — Unilever R&D, Liverpool
Predictive ML across global factories generating $50M+ of value, and the largest R&D automation programme in Unilever's history: robotic platforms that raised throughput 20× and scaled data collection from hundreds to millions of points per day.
- 2017
Automation Engineer — Oman LNG (via SECL UK), Sur
Tendered, won and delivered ~$500K of control-systems projects on time at a live LNG plant, leading field teams and training local engineers, all alongside my Master's.
Education & credentials
Education
- Data Analyst Fellowship, BCS — Distinction, 2019–2020
- MSc Process Modelling, University of Birmingham — Merit, 2017
- BEng Process Engineering, Lancaster University — 2:1, 2016
- Associate Member IChemE · RITTech
Languages & eligibility
- English — native · German — B1/B2
- UK citizen · EU Blue Card (Germany)
Toolbox
- Software
- Python · TypeScript / Node · SQL · R · MATLAB · C++
- ML / AI
- TensorFlow · PyTorch · Gaussian processes · neural networks · first-principles modelling · LLMs · RAG · multi-agent systems
- Platform
- AWS · Airflow · Docker · InfluxDB · PostgreSQL · Datadog · Linux · CI/CD · MLOps
Contact
Open to senior data science, ML engineering and AI leadership roles.
Reach me on LinkedIn.