● Open to Trust & Safety and AI quality roles · Dublin or remote from Ireland
I measure how decisions get made: moderation quality, policy enforcement, and the AI systems that now take part in them. Seven years, Dublin.
Rules filter. The model reads. A person decides. Every label carries its source.
An evidence-first decision system I built and measured: 2,238 postings, 92.5% agreement with my own decisions.
Read the case study →About me
Prepared answers · not a live chat
Lead case study
An evidence-first decision system I built and run: rules filter, a small model reads, I decide, and every label carries its source.
It has handled 2,238 postings, and the score it uses agreed with 92.5% of 65 of my own decisions it had never seen.
● In a private testing phase. The platform will be opened up and made public once testing is complete; the demo runs on synthetic data.
Personal assistant
An assistant that acts rather than talks: it reads the inbox and the calendar before I wake up, keeps what matters, and does the small things itself, on Telegram.
A recorded conversation; the content shown is illustrative, nothing runs live.
Policy & enforcement · content moderation · integrity operations · risk assessment
SLA 76%→97% · processing time 48h→33h on a safety queue (Conectys)
Quality measurement · search quality · root-cause analysis · calibration
−30% false positives via calibration & RCA
LLM evaluation · Python · n8n · APIs · SQL · prompt engineering
AI quality-dashboard prototype → accepted as the basis for further development (Meta)
Project management · process improvement · training · stakeholder management
Trained & calibrated QA teams at TikTok & Conectys
Project Manager — Problem Integrity Solutions
Co-developed a reusable root-cause analysis approach for integrity quality issues; the quality-measurement dashboard prototype was accepted as a basis for further development.
Data Labelling & AI Content Quality Analyst
Evaluated LLM-judge outputs and moderation decisions across fraud, phishing and other sensitive policy areas.
Search Operations / AI Quality Analyst, Trust & Safety
Evaluated search relevance and quality, including SBS and NDCG, and supported guideline refinement and calibration.
Quality Analyst — Trust & Safety / TikTok Moderation
Redesigned child-safety escalation with a risk matrix, decision tree and SOPs: SLA from 76% to 97%, processing time from 48h to 33h.
I'm open to Trust & Safety, AI operations and quality roles in Dublin or remote-from-Ireland.