Open to opportunities

Ekaterina Filippova

@ekaterinafilippova

Message

LLM evaluation expert specializing in comparative testing and linguistic quality analysis.

China

Message

What I'm looking for

I’m looking for a role focused on LLM/multi-modal evaluation where I can design rubrics, run comparative tests, and deliver reliable, well-documented results—especially when linguistic quality and context (including Russian) matter.

I focus on evaluating and comparing multi-modal AI models using structured, scenario-based testing. I create evaluation rubrics and document how and why model performance differs across contexts.

In my LLM evaluation work, I’m an expert in comparative assessment of multi-modal AI models (Doubao, Yuanbao, DeepSeek vs. ChatGPT, Gemini). I use comparative testing to identify the best-performing model for specific scenarios, including Chinese vs. European contexts.

I also bring strong linguistic analysis skills: I analyze Russian text for logical consistency, cultural nuances, and semantic accuracy. With tools like Microsoft Excel (Pivot Tables) and Google Sheets, plus collaboration in Feishu, DingTalk, WeChat, and Telegram, I’m comfortable turning evaluation results into clear, actionable insights.

Experience

Work history, roles, and key accomplishments

Russian TFL & LLM Evaluator

A.S. Pushkin State Russian Language Institute

Jan 2026 - Present (5 months)

Completed professional retraining in Teaching Russian as a Foreign Language (Methodology). Performed comparative LLM evaluations across multimodal models and created evaluation rubrics while analyzing Russian text for semantic accuracy, logical consistency, and cultural nuances.

LLM Evaluation Evaluation Rubric Design Cultural Nuance Analysis Google Sheets