Thomas H.

Key Skills

Software

Snorkel AI

Other

Internal/Proprietary Tooling

Don't disclose

Top Subject Matter

Llms Domain Expertise

Prompt Engineering

Evaluation Domain Expertise

Top Data Types

Text

Document

Image

Top Task Types

Classification

Question Answering

Computer Programming/Coding

Evaluation/Rating

Data Collection

Fine-tuning

Text Summarization

Text Generation

Object Detection

RLHF

Function Calling

Transcription

Red Teaming

Freelancer Overview

AI DevOps - LLM Evaluation and Benchmarking. Brings 7+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Snorkel AI and Other. Education includes Master of Science, Worldquant University (2027) and Bachelor of Arts, Denison University (2025). AI-training focus includes data types such as Text and labeling workflows including Evaluation, Rating, and Classification.

Labeling Experience

AI DevOps - LLM Evaluation and Benchmarking

Snorkel AIText

Designed and specified multi-step agentic benchmark tasks to evaluate Large Language Model (LLM) performance. Wrote precise task specifications and scoring criteria to ensure comprehensive assessment of models. Analyzed model failure modes and developed solutions for improved evaluation quality. • Developed new benchmarks for LLM assessment • Authored clear rubrics and evaluation frameworks • Utilized prompt engineering to guide AI responses • Collaborated with DevOps to automate test suites and validate outcomes

2025 - Present

Research Intern - Disaster Data Labeling

OtherTextClassification

Created and implemented BERT-based and LDA models to analyze a large dataset of social media posts during Hurricane Harvey. Facilitated the categorization and labeling of over 400,000 tweets to improve disaster impact analysis. Applied data annotation practices integral to Natural Language Processing (NLP) workflows. • Developed and applied topic modeling for classification • Enhanced dataset quality for AI/ML research • Leveraged NLP techniques for emotion and topic labeling • Contributed annotated data to research publications

2024 - 2024

Education

Work History