For employers

Hire this AI Trainer

Sign in or create an account to invite AI Trainers to your job.

Invite to Job
Joshua Templeman

Joshua Templeman

Expert in LLM evaluation, audio prompting, and rubric generation.

United Kingdom flagBristol, United Kingdom
$25.00/hrExpertLabelboxMercorRemotasks

Key Skills

Software

LabelboxLabelbox
MercorMercor
RemotasksRemotasks
Scale AIScale AI
TolokaToloka
TelusTelus

Top Subject Matter

No subject matter listed

Top Data Types

AudioAudio
ImageImage
TextText

Top Task Types

Audio Recording
Evaluation Rating
Text Generation
Text Summarization
Transcription

Freelancer Overview

I've been an expert in training LLMs for around 3 years now. My experience spans text, audio, and imagery. I've become highly proficient at evaluating and refining model-generated responses – with a strong eye for detail when it comes to fact checking, subediting, and formatting. I've developed strong skills in creating the perfect response to complex prompts – creating and refining rubric criteria, meticulously ensuring accuracy, and crafting concise, well-written answers. These skills have seen me promoted to Senior Reviewer on multiple projects I have worked on. I've also gained valuable work experience in AI red-teaming, where I've developed creative strategies in stumping, breaking, and finding critical vulnerabilities in AI models. This has allowed me to apply my conceptual thinking to help rid AI models of dangerous responses, bias, and privacy violations. Here, I have helped tutor others in refining and iterating their skills in this space.

ExpertEnglishSpanish

Labeling Experience

Mercor

Multimango

MercorTextBounding Box
A range of tasks. Ranging from ranking, bounding box generation, exraction, and summarization.

A range of tasks. Ranging from ranking, bounding box generation, exraction, and summarization.

2025 - 2025
Scale AI

High Noon

Scale AITextEvaluation Rating
Rubric generation around complex, adversarial prompting. Subsequent reviews of AI models.

Rubric generation around complex, adversarial prompting. Subsequent reviews of AI models.

2025 - 2025
Scale AI

Xylophone

Scale AIAudioAudio Recording
Audio prompting across a range of domains. Reviewing transcripting skills and testing accents.

Audio prompting across a range of domains. Reviewing transcripting skills and testing accents.

2025 - 2025

Education

U

University of Bristol

Master of Science, International Development

Master of Science
2022 - 2023
U

University of Bristol

Bachelor of Science, Politics and International Relations

Bachelor of Science
2019 - 2022

Work History

C

Cognizant Moment

Copywriter

Bristol
2024 - Present
R

Resource Media

Junior Editor

Bristol
2023 - 2024