Looking for a job

Raymond Julian Gates

@raymondjuliangates

Message

LLM evaluator at TELUS Digital AI who analyzed model failures and turned findings into training recommendations.

United States

Message

At TELUS Digital AI, I evaluated large language model responses for factuality, safety, relevance, and instruction following. I analyzed failure patterns and translated my findings into structured recommendations for AI training and model improvement.

At Sama and RWS, I supported AI training workflows through data annotation, validation, and quality assessment. My research projects explored synthetic-data evaluation, LLM-as-a-Judge methods, and repeatable workflows for assessing model behavior.

Experience

Work history, roles, and key accomplishments

LLM Evaluator / AI Response Evaluator

TELUS Digital AI

Jun 2024 - Mar 2025 (9 months)

Evaluated LLM outputs against quality, factuality, safety, and instruction-following criteria. Conducted error analysis and comparative evaluations to identify model failures and support AI training improvements.

LLM Evaluation Error Analysis Comparative Evaluation Fact Checking Data Annotation Prompt Evaluation Research Documentation

Quality Analyst / Data Annotator

Sama

Jan 2022 - Dec 2024 (2 years 11 months)

Performed quality assurance and annotation for AI training datasets, reviewing labeled data for accuracy and consistency. Identified errors and collaborated on data-quality improvements.

Data Annotation Quality Assurance Data Labeling Error Categorization Multimodal Annotation Data Quality

AI Data Specialist

RWS

Jan 2020 - Dec 2022 (2 years 11 months)

Supported AI and machine-learning initiatives through data preparation, annotation, and quality assessment. Reviewed training datasets and applied analytical methods to identify data anomalies and labeling inconsistencies.

Data Preparation Data Annotation Data Validation NLP Text Classification Quality Control Research