Open to opportunities

Igor Polishchuk

@igorpolishchuk

Message

I evaluate Russian-language AI outputs through rigorous language, dialogue, and safety analysis.

Russian Federation

Message

What I'm looking for

I'm looking for remote work evaluating Russian-language AI outputs, analyzing dialogue quality and safety, fact-checking content, and producing clear evidence-based written assessments.

I led authorship for AI Safety Camp’s research track, Psychological Risk Pathways in AI Use: An Exploratory Contribution to User Wellbeing and Safety, developing an original framework that informed the broader track.

I analyze frontier-model behavior, failure modes, and risks for vulnerable users, with close attention to framing, context, consistency, and subtle human-AI dialogue patterns. My evaluations combine evidence synthesis, fact-checking, and clear written justification.

As a native Russian speaker with B2 English, I provide structured, guideline-based assessment of nuanced Russian-language content and AI outputs.

Experience

Work history, roles, and key accomplishments

Research Participant, Lead Author

AI Safety Camp

Lead author of a research track on psychological risk pathways in AI use, developing an original research framework and analyzing frontier-model behavior and potential risks to vulnerable users.

AI Safety Research Human AI Interaction Risk Analysis Evidence Synthesis