Sochi A.

Key Skills

Software

Other

Mercor

Micro1

Mindrift

Remotasks

Toloka

Top Subject Matter

AI optimization

model evaluation

and safety

Top Data Types

Text

Video

Image

Top Task Types

RLHF

Segmentation

Object Detection

Text Generation

Freelancer Overview

AI/Data Labeling & Annotation (Education Project) — RLHF & RLAIF, Model Evaluation & Red Teaming. Brings 11+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other. Education includes Bachelor of Science, Alex Ekwueme Federal University Ndufu Alike Ikwo (2025) and High School Diploma, Government Technical College (2020). AI-training focus includes data types such as Text and labeling workflows including RLHF.

Labeling Experience

AI/Data Labeling & Annotation (Education Project) — RLHF & RLAIF, Model Evaluation

TextRLHF

This experience focuses on AI optimization activities related to RLHF and RLAIF for model improvement. The work includes evaluating model behavior and participating in red teaming to identify weaknesses and areas for refinement. It supports iterative alignment and performance tuning of AI systems for more reliable outputs. • RLHF & RLAIF model optimization • Model evaluation for quality and safety • Red teaming to surface failure modes • Ongoing AI training and alignment work

2025 - Present

AI/Data Labeling & Annotation (Education Project) — RLHF & RLAIF, Model Evaluation

VideoRLHF

This experience focuses on AI optimization activities related to RLHF and RLAIF for model improvement. The work includes evaluating model behavior and participating in red teaming to identify weaknesses and areas for refinement. It supports iterative alignment and performance tuning of AI systems for more reliable outputs. • RLHF & RLAIF model optimization • Model evaluation for quality and safety • Red teaming to surface failure modes • Ongoing AI training and alignment work

2025 - Present

AI/Data Labeling & Annotation (Education Project) — RLHF & RLAIF, Model Evaluation

OtherImageRLHF

This experience focuses on AI optimization activities related to RLHF and RLAIF for model improvement. The work includes evaluating model behavior and participating in red teaming to identify weaknesses and areas for refinement. It supports iterative alignment and performance tuning of AI systems for more reliable outputs. • RLHF & RLAIF model optimization • Model evaluation for quality and safety • Red teaming to surface failure modes • Ongoing AI training and alignment work

2025 - Present

Education

Work History