TYLER BUNN
Hidden Springs,USA
Summary
Meticulous AI Data Annotator and Evaluator with expertise in assessing AI-generated content across text, image, and video formats. Proficient in identifying reasoning errors, instruction-following failures, and quality inconsistencies using structured evaluation rubrics. Demonstrates strong analytical problem-solving skills and thrives in fast-paced remote environments.
Overview
4
4
years of professional experience
Work History
AI Data Annotator & Quality Reviewer
Handshake AI
02.2025 - Current
- Annotated and reviewed AI-generated outputs for accuracy, clarity, and adherence to rubric standards
- Evaluated model responses with structured scoring and ranking systems to ensure quality
- Flag unsafe, incorrect, or low-quality outputs for correction and retraining pipelines
- Support iterative improvements to annotation guidelines and evaluation standards
- Collaborated asynchronously with distributed QA and labeling teams to enhance consistency and reliability
AI Data & Content Evaluator
Mercor
12.2024 - Current
- Evaluated AI-generated outputs across text, image, and video datasets for correctness, tone, safety, and instruction adherence, ensuring high-quality standards
- Apply structured rubrics to identify reasoning errors, hallucinations, and contextual inconsistencies
- Performed comparative ranking of model responses to enhance training data quality and accuracy
- Provided structured feedback to enhance annotation consistency and clarify guidelines, supporting team alignment
- Maintain high accuracy and throughput in deadline-driven remote workflows
Independent AI Evaluation & Prompt Analysis
Self-Directed Projects
12.2021 - Current
- Analyzed LLM behavior across reasoning, instruction-following, and contextual understanding tasks
- Identified common failure modes including hallucinations, logic inconsistencies, and instruction misalignment
- Acquired familiarity with evaluation frameworks aligned with production AI annotation pipelines
- Gained practical experience with AI systems by testing prompts, evaluating responses, and practicing structured labeling
Education
B.S. - Computer Science
Boise State University
01-2028
Skills
- AI annotation
- Dataset labeling
- Data Quality Assurance
- Quality Assurance
- Error detection
- Content moderation
- Instruction-Following Evaluation
- Prompt analysis
- Data Interpretation
- Python (Foundational)
- Computational Thinking
- Collaboration Tools
Timeline
AI Data Annotator & Quality Reviewer
Handshake AI
02.2025 - Current
AI Data & Content Evaluator
Mercor
12.2024 - Current
Independent AI Evaluation & Prompt Analysis
Self-Directed Projects
12.2021 - Current
B.S. - Computer Science
Boise State University