Matthew H.

Key Skills

Software

Don't disclose

Data Annotation Tech

Top Subject Matter

Multimodal AI output evaluation for LLM training pipelines

LLM response evaluation

rubric scoring

Top Data Types

Image

Text

Top Task Types

Prompt + Response Writing (SFT)

Freelancer Overview

Handshake — Artificial Intelligence Annotator / Trainer. Brings 2+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Don't disclose and Data Annotation Tech. Education includes Bachelor of Science, University of California, Los Angeles (UCLA) (2027) and Associate in Science for Transfer in Biology, Mt. San Antonio College (2025). AI-training focus includes data types such as Image and Text and labeling workflows including Evaluation, Rating, and Prompt + Response Writing (SFT).

Labeling Experience

Data Annotation Tech — AI Response Evaluator / Data Annotator

Data Annotation TechTextPrompt + Response Writing (SFT)

Designed evaluation rubrics to score and rank AI-generated responses across multiple LLMs using structured quality criteria. Evaluated model outputs to identify factual errors, reasoning gaps, ambiguity, and qualitative differences in response quality. Authored clear, evidence-based rationales justifying rankings and documenting rubric-based scoring decisions. • Rubric design for structured response quality scoring. • Identification of factual errors, reasoning gaps, and ambiguity. • Evidence-based rationale writing for model rankings. • Analysis of prompt types to surface systematic model weaknesses.

2026 - Present

Handshake — Artificial Intelligence Annotator / Trainer

Don't discloseImage

Performed AI training and evaluation for LLM pipelines in collaboration with leading AI research labs. Evaluated multimodal AI outputs using structured, project-specific guidelines to assess quality, accuracy, and alignment. Applied consistent annotation criteria to support reproducible evaluation across diverse task formats and throughput requirements. • Multimodal evaluation across image, video, and audio. • Quality/accuracy/alignment rating against detailed guidelines. • Structured annotation criteria for consistency and unbiased results. • High-throughput work while upholding defined quality standards.

2025 - Present

Education

Work History