Damir Rudenko

Key Skills

Software

Mercor

CVAT

Internal/Proprietary Tooling

Top Subject Matter

No subject matter listed

Top Data Types

Audio

Document

Image

Text

Video

Top Label Types

Evaluation Rating

Bounding Box

Classification

Freelancer Overview

AI Quality Assurance Specialist focused on high-quality data labeling and RLHF (Reinforcement Learning from Human Feedback). I specialize in validating LLM outputs for accuracy, safety, and cultural nuance across Ukrainian, Russian, Polish, and English. Key responsibilities include:Performing systematic A/B testing and ranking of model responses (SFT/RLHF).Designing prompt engineering strategies to improve instruction-following.Developing automated data processing workflows using n8n and Zapier.Evaluating model guardrails to minimize hallucinations and bias in complex multilingual datasets.

Labeling Experience

Quality Assurance for AI-Generated Video

Internal Proprietary ToolingVideoClassificationEvaluation Rating

Evaluated AI-generated video clips based on visual consistency, motion smoothness, and adherence to the text prompt. Identified common artifacts and "hallucinations" in the video outputs to help refine the generative model.

Evaluated AI-generated video clips based on visual consistency, motion smoothness, and adherence to the text prompt. Identified common artifacts and "hallucinations" in the video outputs to help refine the generative model.

2025 - 2025

Video Content Labeling for Computer Vision

CVATVideoBounding Box

Focused on identifying and labeling moving objects in video sequences. Tasks included drawing bounding boxes around vehicles and pedestrians and ensuring consistent object ID tracking across multiple frames. Followed strict quality guidelines to provide high-accuracy data for training computer vision models.

Focused on identifying and labeling moving objects in video sequences. Tasks included drawing bounding boxes around vehicles and pedestrians and ensuring consistent object ID tracking across multiple frames. Followed strict quality guidelines to provide high-accuracy data for training computer vision models.

2025 - 2025

AI Quality Assurance and Model Testing Specialist

MercorTextEvaluation Rating

In this role, I conducted systematic quality assurance testing on AI outputs to evaluate factual accuracy, logical consistency, and detect hallucinations. I optimized prompts for large language models to improve relevance and minimize undesirable outputs. I performed multilingual validation on generated content across four languages. • Utilized prompt engineering to refine output quality • Developed automated workflows for testing using n8n • Conducted A/B testing on GPT-4 and Claude 3.5 outputs • Analyzed edge case failures and contributed to safety guardrail documentation

In this role, I conducted systematic quality assurance testing on AI outputs to evaluate factual accuracy, logical consistency, and detect hallucinations. I optimized prompts for large language models to improve relevance and minimize undesirable outputs. I performed multilingual validation on generated content across four languages. • Utilized prompt engineering to refine output quality • Developed automated workflows for testing using n8n • Conducted A/B testing on GPT-4 and Claude 3.5 outputs • Analyzed edge case failures and contributed to safety guardrail documentation

2024 - 2024

Education

Work History