Victor B.

Key Skills

Software

Scale AI

Other

Top Subject Matter

LLM output evaluation and creative writing quality assessment

Prompt engineering

dataset creation

Top Data Types

Text

Document

Top Task Types

Prompt + Response Writing (SFT)

Red Teaming

Freelancer Overview

AI Trainer & Data Annotator at Luel-AI. Brings 5+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Core strengths include Scale AI and Other. Education includes Prompt Engineering Certificate, N/A (2020). AI-training focus includes data types such as Text and labeling workflows including Evaluation, Rating, and Prompt + Response Writing (SFT).

Labeling Experience

Red-teaming activities (part of AI Trainer & Data Annotator work at Luel-AI)

OtherTextRed Teaming

Performed red-teaming and safety analysis to uncover vulnerabilities in LLM instruction following. Identified jailbreak-prone instruction patterns and edge-case failures to inform safer model behavior. Applied consistent reporting to support training and mitigation efforts. • Tested prompts to elicit unsafe or undesired outputs • Logged failure modes and safety weaknesses for review • Assessed robustness under adversarial or ambiguous instructions • Contributed to iterative safety improvements

2023 - Present

AI Trainer & Data Annotator at Luel-AI

Scale AIText

Evaluated and ranked LLM-generated responses using structured quality rubrics across accuracy, coherence, tone, and helpfulness. Provided iterative feedback on output quality to support model improvement cycles and maintain consistent scoring standards. Worked on creative writing focused evaluation including plot logic and character voice assessment. • Conducted side-by-side comparisons and rubric-based scoring • Tracked inter-annotator agreement and consistency across evaluations • Identified subtle reasoning errors and edge-case failures • Supported iterative training sprints with detailed written critiques

2023 - Present

Freelance AI Content Specialist (Independent/Remote)

OtherTextPrompt + Response Writing (SFT)

Designed and tested complex prompt sequences for LLM applications across creative, educational, and conversational tasks. Produced training datasets that captured diverse writing styles, genres, and narrative structures to improve model versatility. Evaluated chatbot and generative AI outputs by flagging inconsistencies, bias, and hallucinations for client deliverables. • Created evaluation criteria and rubrics aligned to client goals • Generated high-quality prompt-response examples for supervised training use • Performed quality checks for safety and helpfulness • Documented findings and collaborated with clients on requirements

2022 - 2023

Education

Work History