For employers

Hire this AI Trainer

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

Invite to Job
P
Perpetua A.

Perpetua A.

Technical AI Evaluator | Data Labeling & Model Response Reviewer

USA flagOakland, Usa

Key Skills

Software

No software listed

Top Subject Matter

My strongest subject matter areas are AI training
data labeling
technical model evaluation
DevOps
cloud infrastructure

Top Data Types

ImageImage
VideoVideo
TextText

Top Task Types

MappingMapping
Text SummarizationText Summarization
Emotion RecognitionEmotion Recognition
Question AnsweringQuestion Answering
Text GenerationText Generation
SegmentationSegmentation

Freelancer Overview

I have hands-on experience supporting AI/ML and technical data workflows through DevOps, automation, documentation, and quality review. My background includes working with AI/ML engineers to support model deployment pipelines, monitor ML workloads, validate technical outputs, and improve reliability across cloud-based environments. I have also reviewed logs, deployment results, code changes, and system behavior to identify errors, inconsistencies, and quality issues, which aligns closely with data labeling, AI response evaluation, and model output review. In addition, I have strong experience following structured guidelines, writing clear technical documentation, reviewing content for accuracy, and using tools such as Python, Bash, Git, GitHub Actions, Jenkins, Docker, Kubernetes, AWS, and Azure. This gives me a strong foundation for AI training tasks such as prompt-response evaluation, data annotation, classification, hallucination detection, rubric-based scoring, technical content review, and coding-related model evaluation. My DevOps and cloud background allows me to handle both general data labeling work and more advanced technical AI evaluation tasks.

Labeling Experience

Yes

Yes. I have worked as an AI evaluator on Handshake, reviewing AI-generated responses against task guidelines and scoring rubrics. My work includes checking accuracy, instruction-following, relevance, clarity, hallucinations, and overall response quality, then providing structured feedback to improve model performance.

Not specified

Education

B

Bachelor of Engineering in Computer Engineering, plus professional training in AWS Cloud Computing, DevOps Engineering,

Degree not specified

Not specified
Not specified

Work History

A

accuracy

I evaluate AI-generated responses

Location not specified
Not specified