Felix Garcia

Key Skills

Software

Appen

Axiom AI

HiveMind

Labelbox

LabelImg

Label Studio

Mercor

Remotasks

Scale AI

Surge AI

Toloka

Top Subject Matter

No subject matter listed

Top Data Types

Computer Code Programming

Document

Text

Top Task Types

Computer Programming Coding

Data Collection

Evaluation Rating

Prompt Response Writing SFT

RLHF

Freelancer Overview

With over three years of experience in AI training and data labeling, I have contributed to large-scale projects involving data science, routing, and code understanding for global technology partners such as Google. My expertise spans Reinforcement Learning from Human Feedback (RLHF), prompt and response evaluation, and golden data generation for model fine-tuning and quality assurance. I specialize in evaluating and refining model outputs across programming, text, and reasoning domains, applying precise annotation standards and consistency checks. Proficient with leading platforms like Scale AI, Outlier AI, and Remotasks, I bring strong analytical, linguistic, and technical skills that ensure reliable, high-quality data pipelines for AI systems.

Labeling Experience

RLHF and Prompt Evaluation for Code and Text Models

Scale AIComputer Code ProgrammingRLHFFine Tuning

Worked on large-scale data labeling and evaluation projects focused on improving model reasoning and alignment. Tasks included evaluating and ranking AI model responses using RLHF methodologies, curating golden responses for supervised fine-tuning, and annotating code-based prompts to enhance multi-language routing accuracy. Ensured data quality through double-blind reviews, consistency checks, and adherence to platform-specific annotation guidelines.

Worked on large-scale data labeling and evaluation projects focused on improving model reasoning and alignment. Tasks included evaluating and ranking AI model responses using RLHF methodologies, curating golden responses for supervised fine-tuning, and annotating code-based prompts to enhance multi-language routing accuracy. Ensured data quality through double-blind reviews, consistency checks, and adherence to platform-specific annotation guidelines.

2021

Education

Work History