Ruslan Davidenko ruslandavidenko

AI Systems & Evaluation Engineer | Linux • Docker • Python • Benchmarking • RLHF 🔗 Portfolio: https://ruslandavidenko.github.io/

AI Annotation QA System

AI annotation quality assurance workflows for ranking, relevance scoring, factuality checks, and safety evaluation.

This repository contains AI annotation QA and evaluation workflows used for validating AI-generated outputs and human feedback pipelines.

Focused areas include:

Python • Pandas • NumPy • OpenAI API • NLP Tooling • Evaluation Pipelines

🚧 Active Development

Ruslan Davidenko
AI Systems & Evaluation Engineer

ai-annotation-qa-system ai-annotation-qa-system Public

AI annotation QA workflows for ranking, relevance scoring, factuality checks, and safety evaluation.

Python 1
graph-neural-network-benchmarking graph-neural-network-benchmarking Public

Benchmarking Graph Neural Network architectures including GCN, GAT, and GraphSAGE
llm-evaluation-rlhf-pipeline llm-evaluation-rlhf-pipeline Public

LLM evaluation, RLHF scoring, hallucination analysis, and AI safety benchmarking pipeline built with Python.

Python 1
terminal-bench-log-summary-audit terminal-bench-log-summary-audit Public

Deterministic Linux log analysis benchmark task for AI-agent evaluation using Docker and Terminal-Bench

Python