
01 · Logistics & Travel
FLYBIZ
A business website for a logistics and travel company, designed to present its services and provide customers with an accessible online presence.
- React
- Tailwind CSS
- Responsive Design
Full-Stack Web Developer | AI Trainer & Evaluator
I'm BEN JAHSON TOJAH, a Full-Stack Web Developer and AI Training & Evaluation Professional. I build websites and digital solutions for businesses while contributing to the development and evaluation of intelligent AI systems.
01 — About
I build modern, responsive digital experiences that help businesses establish their online presence and operate more effectively. I care about products that are useful, accessible, and quietly well designed — the kind people can use without thinking about it.
Alongside software development, I contribute to AI training and evaluation workflows, helping improve the quality, accuracy, and usefulness of AI-generated outputs. Reviewing how models respond has sharpened how I think about clarity, correctness, and the people on the other side of the screen.
The two disciplines inform each other: building teaches me what good output looks like in practice, and evaluating teaches me to question it carefully.
02 — Selected Work

01 · Logistics & Travel
A business website for a logistics and travel company, designed to present its services and provide customers with an accessible online presence.
02 · Education
An educational institution website designed to communicate school information and provide a professional digital presence.

03 · Travel Consultancy
A website developed for a travel consultancy business to showcase its services and establish an online presence.
03 — Expertise
A / Frontend
B / Backend & Development
C / AI Training & Evaluation
04 — AI Training & Evaluation
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
Reviewing language model responses for accuracy, helpfulness, tone, and completeness.
Rating outputs against structured rubrics and explaining the reasoning behind each judgement.
Checking whether a response actually does what the prompt asked — including constraints and format.
Assessing how faithfully generated images reflect the written prompt.
Comparing generated images against reference inputs for identity, style, and detail consistency.
Flagging artefacts, composition issues, and outputs that conflict with responsible AI guidelines.
05 — Contact
Whether you're looking to build a website, improve your digital presence, or collaborate on technology projects, I'd be happy to hear from you.