AI Evaluation Specialist with hands-on experience training, annotating and aligning LLMs and multimodal systems. I bring a rare blend of analytical precision and narrative intelligence — spotting reasoning gaps, hallucinations, and tone failures that scoring rubrics alone miss.
London Area, United Kingdom
AI Evaluation Specialist · LLM & Multimodal AI
About
I spend my time at the edge of language and logic — evaluating how large language models interpret prompts, where alignment breaks down, and where nuance or thematic depth gets quietly lost.
My background as a writer trains me to read closely. I notice tone, subtext, emotional texture, and the shallow synthesis that scoring rubrics often miss. My 15 years in contracts, compliance and operations trained me to document precisely, work to standards, and stay reliable under pressure — the exact muscles that AI evaluation, annotation and remote support work demand.
Whether the task is ranking model responses, annotating multimodal data, writing structured justifications, or supporting a remote team with steady, dependable execution — I show up the same way: careful, curious, and accountable.
What I do
AI evaluation is the core. Writing, research and remote support are the supporting strengths that make me a flexible hire for small teams and project owners.
Assessing model outputs for instruction adherence, reasoning, coherence, and safety across text, image and video.
Labelling, tagging and categorising datasets to QA standards across text, image and video tasks.
SEO-aware long & short-form content across culture, lifestyle and personal development. Sharp at editing AI-assisted drafts.
Drawing on 15+ years in contracts, compliance and operations — reliable, structured remote execution for busy teams.
Core toolkit
Experience
Feb 2026 – Mar 2026 · Remote
High-precision annotation project evaluating AI-generated visual content. Assessed images and video against detailed prompts — rating instruction adherence, image consistency, visual quality and naturalness, and writing concise justifications to support model refinement.
Oct 2025 – Feb 2026 · Remote
Structured data annotation and qualitative evaluation supporting LLM training and alignment. Analysed responses to complex prompts for narrative comprehension, symbolic interpretation, emotional nuance, and long-form reasoning — flagging shallow synthesis, contextual misalignment and edge-case behaviour.
May 2020 – Present · Remote
Long and short-form content across culture, digital lifestyle, creativity and personal growth. SEO-optimised articles, brand-voice work, and refining AI-assisted drafts for clarity, tone alignment and structural coherence.
2024 – 2025
Closing chapter of 15+ years in contracts, compliance and operations — building structured thinking, QA discipline and cross-team coordination skills that now underwrite my AI and remote-work practice.
Credentials
Passed the micro1 AI Interview and certified as an AI Language Researcher & Data Annotation Specialist — a third-party signal that the quality is real, not just claimed.
Certified by micro1
AI Language Researcher & Data Annotation Specialist
Drop certificate image at assets/images/micro1-certificate.jpeg
Get in touch
I'm available now for AI evaluation, annotation, writing and remote support work — short briefs or longer engagements, fully remote, ready to start immediately.
Based in London · Working with teams worldwide