Brandon Hayes

Key Skills

Software

AWS SageMaker

Top Subject Matter

Document Classification

Internal Knowledge Management

Top Data Types

Text

Image

Top Task Types

Fine Tuning

Freelancer Overview

AI Engineer – Fine-tuning and data preparation for document classification. Brings 6+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include AWS SageMaker. Education includes Master of Science, University of Texas at Austin (2020). AI-training focus includes data types such as Text and labeling workflows including Fine-tuning.

Labeling Experience

AI Engineer – Fine-tuning and data preparation for document classification

Aws SagemakerTextFine Tuning

Fine-tuned BERT-based models for document classification as part of developing advanced natural language processing capabilities. This process involved curating and preparing labeled datasets, followed by systematically training and validating models to optimize performance. Consistent evaluation methods were utilized to ensure robust F1-scores and accuracy for deployment in production environments. • Labeled and curated text data specific to company knowledge domains. • Used iterative supervised fine-tuning cycles to enhance document classification accuracy. • Collaborated with team members to verify annotated datasets and resolve ambiguities. • Optimized dataset quality for improved NLP model outcomes.

Fine-tuned BERT-based models for document classification as part of developing advanced natural language processing capabilities. This process involved curating and preparing labeled datasets, followed by systematically training and validating models to optimize performance. Consistent evaluation methods were utilized to ensure robust F1-scores and accuracy for deployment in production environments. • Labeled and curated text data specific to company knowledge domains. • Used iterative supervised fine-tuning cycles to enhance document classification accuracy. • Collaborated with team members to verify annotated datasets and resolve ambiguities. • Optimized dataset quality for improved NLP model outcomes.

2022 - Present

Education

Work History