Soyang F.

Key Skills

Software

Don't disclose

Top Subject Matter

AI model output evaluation and quality assurance

Recruitment pipeline evaluation (transferable to AI output review)

AI model assessment and quality assurance

Top Data Types

Text

Top Task Types

Data Collection

Evaluation/Rating

Computer Programming/Coding

Transcription

Question Answering

Text Summarization

Freelancer Overview

AI Model Assessment Specialist (Part-Time) — Job Robotic. Brings 8+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Don't disclose. Education includes Bachelor's Degree, FONAB Polytechnic University Institute (2026) and Associate Degree, National Polytechnic University Institute (2021). AI-training focus includes data types such as Text and labeling workflows including Evaluation and Rating.

Labeling Experience

AI Evaluation Specialist — SHSWS Solutions.com

Don't discloseText

Assessed AI-generated outputs for accuracy, clarity, and adherence to instructions across diverse task types. Applied structured annotation and review processes within a technical, product-oriented quality context. Identified recurring patterns and inconsistencies to inform quality improvement initiatives and reduce future errors. • Instruction-following and quality checks • Structured annotation and review workflows • Pattern detection in model responses • Support quality improvement through systematic findings

2026 - Present

Recruitment Specialist (Remote) — Daniel Pinto Consulting Firm

Don't discloseText

Screened and evaluated candidates against structured criteria, mirroring annotation and review processes used in AI evaluation workflows. Delivered structured feedback reports to hiring managers, emphasizing evidence-based findings over assumptions. Maintained quality assurance standards throughout the recruitment pipeline to uphold data integrity and consistency. • Candidate assessment using structured criteria • Evidence vs. assumption distinction in evaluations • QA and data integrity across assessment records • Multi-assessment prioritization under tight deadlines

2025 - Present

AI Model Assessment Specialist (Part-Time) — Job Robotic

Don't discloseText

Evaluated AI model outputs using structured checks for instruction-following, factual accuracy, and overall response quality. Conducted consistent structured annotation processes across an extended engagement to ensure sustained reliability and adherence to quality standards. Reported and validated findings as part of an ongoing assessment workflow to support improvement decisions. • Instruction-following review of model responses • Evidence-based assessment to distinguish accuracy from assumptions • Structured annotation to capture quality dimensions • Sustained quality control across multiple evaluation cycles

2019 - 2026

Recruitment Specialist (Remote) — Gruntwork

Don't discloseText

Reviewed candidate information for remote-first software engineering roles using structured criteria aligned with requirements. Assessed clarity and accuracy of written or technical outputs and provided feedback to improve screening decisions. Used asynchronous collaboration practices to maintain consistent evaluation standards across time zones. • Structured candidate output review • Clarity and accuracy assessment against requirements • Actionable feedback for candidates and teams • Data integrity and consistency maintenance

2024 - 2025

Education

Work History