Expertise
What I know, organised plainly.
01 — Expertise
Tools I build with, and what I evaluate.
A / Frontend
- React.js
- JavaScript
- TypeScript
- Vite
- Tailwind CSS
- Responsive Web Design
B / Backend & Development
- Backend Development
- Python
- API Integration
- Web Application Development
- GitHub
- Supabase
- Vercel
C / AI Training & Evaluation
- AI Model Training
- LLM Response Evaluation
- AI Output Quality Assessment
- Instruction Following Evaluation
- Text-to-Image Evaluation
- Reference-to-Image Evaluation
- Visual Quality Assessment
- AI Alignment and Responsible AI Review
02 — AI Training & Evaluation
Working With AI. Improving What Comes Next.
Through project-based work on AI training and evaluation platforms, including Outlier and Handshake, I review and assess model outputs against detailed guidelines. The work is careful and methodical: reading closely, judging fairly, and writing feedback that helps models become more accurate and more useful.
Platform-based project work · Outlier · Handshake
- 01
AI response evaluation
Reviewing language model responses for accuracy, helpfulness, tone, and completeness.
- 02
Model output quality assessment
Rating outputs against structured rubrics and explaining the reasoning behind each judgement.
- 03
Instruction-following assessment
Checking whether a response actually does what the prompt asked — including constraints and format.
- 04
Text-to-image output evaluation
Assessing how faithfully generated images reflect the written prompt.
- 05
Reference-image consistency
Comparing generated images against reference inputs for identity, style, and detail consistency.
- 06
Visual quality & alignment
Flagging artefacts, composition issues, and outputs that conflict with responsible AI guidelines.