Peyton B.

Key Skills

Software

Other

Top Subject Matter

Multimodal AI evaluation for text-to-image generation

Multimodal AI evaluation for image-to-image generation

Multimodal AI evaluation for audio/video generation

Top Data Types

Text

Image

Audio

Top Task Types

Object Detection

Question Answering

Text Generation

Evaluation/Rating

Freelancer Overview

AI Model Evaluator (Handshake AI · Project Hedgehog / Project Voyager) — Text-to-image evaluation. Brings months of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other. Education includes Bachelor of Science, Utah State University (2025) and High School Diploma, Bingham High School. AI-training focus includes data types such as Text, Image, and Audio, and labeling workflows including Evaluation and Rating.

Labeling Experience

AI Model Evaluator (Handshake AI · Project Voyager) — Audio/video evaluation

OtherVideoObject Detection

Conducted audio and video evaluations by assessing alignment between prompts and the generated multimodal content. Rated the degree to which outputs matched the intended meaning and context described in prompts. Delivered structured feedback to support reliable signals for model training. • Evaluated prompt-to-output alignment for multimodal generation • Assessed quality and relevance of audio components • Reviewed outputs for consistency with evaluator criteria • Completed audio/video checks across active projects

2024 - Present

AI Model Evaluator (Handshake AI · Project Hedgehog) — Image-to-image evaluation

OtherImageEvaluation/Rating

Evaluated image-to-image transformations by judging fidelity, style consistency, and the presence of artifacts in generated outputs. Used repeatable assessment rubrics to compare outputs against expected transformation intent. Supplied detailed evaluator feedback to help guide downstream model refinements. • Measured fidelity to input content and transformation goals • Checked style consistency with prompt and expected aesthetics • Identified artifacts and quality defects in outputs • Contributed evaluation ratings for three concurrent projects

2024 - Present

AI Model Evaluator (Handshake AI · Project Hedgehog) — Text-to-image evaluation

OtherTextEvaluation/Rating

Evaluated text-to-image AI outputs by assessing accuracy, prompt adherence, and visual quality for training feedback loops. Applied consistent criteria across multiple tasks to produce reliable evaluation signals for model improvement. Provided structured qualitative ratings and observations to support iterative AI training decisions. • Rated accuracy relative to prompts and expected content • Checked prompt adherence and interpretation fidelity • Assessed visual quality and coherence of generated images • Delivered high-quality evaluator feedback across ~100 tasks

2024 - Present

Education

Work History