Dion F.

Key Skills

Software

Other

Top Subject Matter

Commercial construction (estimating, proposals, contracts, marketing, operations)

Technical documentation and business workflow automation (construction domain)

Technical writing and research synthesis (construction estimating and proposals)

Top Data Types

Text

Top Task Types

RLHF

Text Summarization

Freelancer Overview

AI Evaluator / Technical Reviewer (factuality and quality assurance). Brings 37+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other. AI-training focus includes data types such as Text and labeling workflows including Evaluation, Rating, and RLHF.

Labeling Experience

AI-Assisted Content Generation & Review (summarization + QA)

OtherTextText Summarization

Generated structured summaries and organized complex technical information using large language models. Transformed raw technical content into clearer, more usable formats for downstream documentation and decision-making. Validated summaries for accuracy and completeness as part of content quality review. • Summarized technical information into concise, structured forms • Organized and reformatted complex data for proposals and operations • Compared alternatives across outputs to improve coverage • Reviewed for accuracy and completeness prior to use

2020 - Present

AI Trainer / Prompt Engineer (human feedback + prompt optimization)

OtherTextRLHF

Performed human feedback and evaluation loops by reviewing AI-generated content and steering improvements through iterative prompt refinement. Designed prompts to improve reasoning consistency, output quality, and structured results for technical documentation and business workflows. Used model comparisons to identify failure modes and guide targeted refinements. • Refined prompts to improve reasoning, consistency, and quality • Used domain checks to validate alignment with construction practices • Iterated on prompt structure to generate more accurate, complete outputs • Compared multiple LLM outputs to surface strengths, weaknesses, and edge cases

2020 - Present

AI Evaluator / Technical Reviewer (factuality and quality assurance)

OtherText

Evaluated AI-generated responses for factual accuracy, completeness, clarity, and overall usefulness using structured quality checks. Assessed whether outputs matched real-world construction practices by applying domain expertise and verifying reasoning and claims. Provided human feedback to improve subsequent AI outputs and prompt effectiveness. • Checked responses for factual errors, missing details, and ambiguity • Rated quality along usefulness and clarity dimensions • Compared outputs conceptually to identify strengths and edge cases • Fed observations back into prompt refinement and workflow improvements

2020 - Present

Work History