For employers

Hire this AI Trainer

Sign in or create an account to invite AI Trainers to your job.

Invite to Job
Carlos Argiz Vazquez

Carlos Argiz Vazquez

Response rating, rewrite, sxs comparison, audio and image rating in Spanish

Spain flagTriacastela, Spain
$20.00/hrEntry LevelAppenData Annotation TechLabelbox

Key Skills

Software

AppenAppen
Data Annotation TechData Annotation Tech
LabelboxLabelbox
Scale AIScale AI
Other
Internal/Proprietary Tooling

Top Subject Matter

Math and Physics responses evaluation
LLM evaluation in Spanish and Galician
Interaction through audio with models and audio responses evaluation.

Top Data Types

AudioAudio
ImageImage
TextText

Top Task Types

Audio Recording
Evaluation Rating
Prompt Response Writing SFT
Text Summarization
Translation Localization

Freelancer Overview

Five months ago I began in the world of AI training, so far my work was related to the evaluation of the LLM responses across different topics and dimensions dimensions, like truthfulness ot the response, instructions following, writting quality, harmfulness, and cultural adaptation. Also, I did audio tasks, interacting with the models through voice and evaluating the responses both in the response quality and audio quality. Some prompt creation and rating in image tasks and prompt generation and rewrite were done as well.

Entry LevelGalicianEnglishSpanishPortuguese

Labeling Experience

Scale AI

Local adaptation

Scale AITextTranslation Localization
Local adaptation checking in model responses

Local adaptation checking in model responses

2024
Appen

Write prompt and review response

AppenImageQuestion Answering
Prompt generation and response rating about a given image.

Prompt generation and response rating about a given image.

2024

Audio rating

OtherAudioClassification
Rating of audio samples across different dimensions.

Rating of audio samples across different dimensions.

2024
Scale AI

Audio evaluation

Scale AIAudioEvaluation Rating
Voice interaction and response evaluation.

Voice interaction and response evaluation.

2024
Scale AI

Evaluation of two model responses

Scale AITextEvaluation Rating
Evaluation of two AI responses across different dimensions and final side by side rating. Also prompt generation and response evaluation and rewrite.

Evaluation of two AI responses across different dimensions and final side by side rating. Also prompt generation and response evaluation and rewrite.

2024

Education

U

UNED

Bachelor's degree in Mechanical Engineering, Engineering

Bachelor's degree in Mechanical Engineering
2008 - 2022

Work History

F

Family Farm

Maintenance and field work

Triacastela
2006 - Present
F

Freelance

AI Trainer

Triacastela
2024 - Present