Hover over the peaks to read the traceTap the peaks to read the trace
I work where measurement meets machine learning: turning noisy signals, from mass spectra to clinical records and language, into results that people can trust and act on.
I am an MSc student in Human-Centred AI at Newcastle University, funded by a Spärck AI Scholarship, and I am looking for PhD opportunities starting in 2027. Before research, I spent seven years as a chemist in analytical and industrial laboratories, then moved into software and AI engineering, most recently building and evaluating LLM systems. If you work on any of the threads below, I would be glad to hear from you.
Three threads that run through my chemistry, engineering and AI work, all about the gap between what a system outputs and what a person can safely do with it.
Spectra, images, sensor streams and health records are messy in similar ways: interference, drift and missing context. I am interested in machine learning that recovers real signal from them, from analytical chemistry to biomedical imaging.
A model, like an instrument, should show what it measured, what it is inferring and what it cannot support, so that people trust it appropriately: neither too much nor too little.
Patients, clinicians and analysts live with a system's output. I want to evaluate and design with them, especially people whose capacity changes from day to day, and to find where models mislead them, including language models that give health advice.
An independent study, designed alongside my MSc.
Do general-purpose language models attribute hypermobility-type symptoms to autism or ADHD when the person describing them is a woman, or neurodivergent? A counterfactual audit across five models, varying gender, neurodivergence, symptom presentation and patient versus clinical framing, with human-validated coding and mixed-effects analysis.
From mass spectra to language models, the work has always been about whether a result can be trusted.
Spärck AI Scholarship. Elected course representative and member of the School of Computing's Student–Staff Committee.
LLMs, retrieval-augmented generation and the evaluation of LLM systems before and after release.
Interfaces for industrial digital twins and predictive maintenance.
GPA 9.4/10, alongside freelance full-stack work.
Grade 9.5/10.
Water and effluent analysis, quality control of hospital products, textile colour development, and teaching laboratories at a brewing school.
Undergraduate dissertation at FURB, supervised by Dr Martinho Rau; graded 9.8/10. The story behind it
Summer research student at De Montfort University, with Prof Richard Brawn.
A year in the UK on the Science without Borders Scholarship.
CNPq research scholarship at FURB, supervised by Prof Jürgen Andreaus: enzymatic treatments, dyeing tests and spectrophotometric analysis of which enzymes significantly improved dyeing.
What I can bring to a lab on day one.
Systems I designed and built, and where they ended up.
Retrieval-augmented generation platform, 2025 to now
My role Sole engineer: RAG pipeline, semantic search and evaluation, first at Straas.tech and now independently
Built at Straas.tech, where it became a company product for customer-service chatbots, and continued since as my own project. It answers from an organisation's own documents with source citations, and says it does not know when those documents do not cover a question.
B2B platform for the fashion supply chain, 2026
My role Co-founder and CTO, sole engineer from concept to live product
Connects clothing brands with garment factories across the production process, with role-based access control and data deletion compliant with Brazil's data protection law (LGPD) through anonymisation. Still in operation.
Career platform for nurses, 2025. 1st place at the Conecta Saúde Health Tech Hackathon
My role Design lead and prototype builder, working closely with two nurses and a business specialist
A working prototype built in three days, with microlearning, career planning and one-to-one scheduling, addressing the lack of structured career progression for nurses and nursing technicians.
Inclusive online group therapy and peer support, 2023 to 2026. Selected for pre-incubation
My role Founder, product and UX
A platform for neurodivergent people and those living with chronic illness, designed around accessibility, safety and dignity rather than engagement. Designing it is where my interest in responsible AI took root: what a system should surface, how it should handle sensitive moments, and when it should defer to a human.
Essays on rigour, AI and the people on the receiving end of both.
Read the essay“Being determined doesn't mean forcing the result you want. It means refusing to claim one the evidence hasn't earned.”
I am happy to talk about PhD projects, collaborations on LLM evaluation, or anything on this page.