Rodriguez Gabriel

Key Skills

Software

Scale AI

Label Studio

CVAT

Labelbox

Prodigy

Top Subject Matter

Large Language Models (LLMs)

AI Safety

Prompt Engineering

Top Data Types

Text

Image

Top Task Types

RLHF

Data Collection

Freelancer Overview

AI Model Evaluator (RLHF & LLM Safety). Brings 6+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Scale AI, Label Studio, and CVAT. Education includes Master of Science, Stanford University (2024) and Bachelor of Science, University of California, Berkeley (2022). AI-training focus includes data types such as Text and labeling workflows including RLHF and Data Collection.

Labeling Experience

AI Model Evaluator (RLHF & LLM Safety)

Scale AITextRLHF

In this role, I evaluated and ranked large language model outputs for correctness, coherence, factual accuracy, and safety using RLHF frameworks. I designed prompt engineering strategies to test LLM reasoning, robustness, and instruction adherence. I also conducted adversarial testing and red teaming to identify vulnerabilities and provided structured feedback for alignment and RL pipelines. • Evaluated LLM outputs across various tasks including code and instruction following • Developed methodologies for adversarial testing and safety assessment • Leveraged prompt engineering in AI evaluation • Delivered structured evaluations to improve model alignment and safety

In this role, I evaluated and ranked large language model outputs for correctness, coherence, factual accuracy, and safety using RLHF frameworks. I designed prompt engineering strategies to test LLM reasoning, robustness, and instruction adherence. I also conducted adversarial testing and red teaming to identify vulnerabilities and provided structured feedback for alignment and RL pipelines. • Evaluated LLM outputs across various tasks including code and instruction following • Developed methodologies for adversarial testing and safety assessment • Leveraged prompt engineering in AI evaluation • Delivered structured evaluations to improve model alignment and safety

2024 - Present

AI Trainer & Data Annotation Specialist

Label StudioTextData Collection

As an AI Trainer and Data Annotation Specialist, I annotated and curated large-scale datasets for training LLMs across text, image, audio, and video modalities. I performed quality evaluation of AI-generated outputs for accuracy, reasoning, and instruction adherence. I also developed structured evaluation rubrics for benchmarking and supported multimodal AI pipelines. • Worked with text, image, audio, and video datasets for LLM training • Ensured dataset quality and completeness • Developed rubrics for model and dataset evaluation • Supported pipelines for NLP, computer vision, and audio processing

As an AI Trainer and Data Annotation Specialist, I annotated and curated large-scale datasets for training LLMs across text, image, audio, and video modalities. I performed quality evaluation of AI-generated outputs for accuracy, reasoning, and instruction adherence. I also developed structured evaluation rubrics for benchmarking and supported multimodal AI pipelines. • Worked with text, image, audio, and video datasets for LLM training • Ensured dataset quality and completeness • Developed rubrics for model and dataset evaluation • Supported pipelines for NLP, computer vision, and audio processing

2023 - 2024

Education

Work History