AI · Healthcare · Data
AI in healthcare,
from scientific depth to real-world systems.
I build machine learning systems, data infrastructure, and the organisational conditions that determine whether any of it gets used. Pharmaceutical background. Engineering discipline. No shortcuts.
What I do
Scientific & Clinical Depth
PharmD and PhD in immuno-oncology with over a decade of experience across life sciences, clinical workflows, and high-dimensional biomedical data. I understand the scientific and regulatory context in which AI must operate.
AI & Data Systems
From single-cell analytics to GenAI-enabled workflows, I design and deliver robust data architectures, machine learning pipelines, and production-grade systems built for real-world complexity.
Product & Market Execution
Bridging product, engineering, and commercial teams across Europe and the US. From prototype to adoption, I turn technical capability into systems that create measurable impact.
Strategy & Leadership
Senior stakeholder alignment, team leadership, and execution in regulated environments. I help organisations define what should be built, why it matters, and how to make it work at scale.
Selected work
Scaling Single-Cell Analysis Beyond Manual Workflows
2019 – PresentDuring the rapid expansion of single-cell technologies, analytical complexity outpaced the capabilities of existing tools. Researchers relied heavily on manual gating and ad hoc workflows, limiting reproducibility and scalability. There was a clear gap between what the data contained and what the software ecosystem could extract in practice.
In Code We Trust: A Decade of Applied ML Writing
2016 – PresentOver the past decade, I have maintained a personal blog focused on machine learning, statistical analysis, and scientific programming. The goal was not content production, but to externalize thinking, working through real problems, documenting approaches, and making complex analytical concepts accessible through concrete examples. The work spans early-stage data exploration, statistical testing, and machine learning workflows.
Designing Feedback Loops for LLM Systems in Production
2025-2026LLM-based knowledge systems often underperform in real-world environments. Not primarily due to model limitations, but because of a persistent gap between what the system returns and what users actually expect. In enterprise contexts, this gap is rarely measured. Feedback is unstructured, inconsistently captured, and not integrated into system improvement. As a result, systems stagnate despite continuous model iteration.
Writing
The Real Bottleneck Isn’t Models or Data. It’s Interfaces.
In fast-moving scientific and AI environments, the real constraint is rarely computation alone. Systems succeed or fail at the interface between methods, workflows, and human adaptation.
Agentic Coding Collapses Build Costs. So Why Is Healthcare Software Still Hard?
As agentic coding drives software creation costs toward zero, competitive advantage shifts toward workflow ownership, governance, operational trust, and the permission to operate.
Explainability Is Not About Explaining the Model
In healthcare and science, trust rarely comes from understanding every internal parameter. Explainability is less about perfect transparency than about building systems humans can safely reason with.
Working on something difficult?
Most AI in healthcare fails because of systems, not models. If you're working on something where that matters, I’m always open to a serious conversation.
Get in touch