Looking for a job

Yana Nezhdanova

@yananezhdanova

AI Language Model Evaluator at Data Light who evaluated LLM responses, curated multilingual datasets, and tested prompts for edge cases.

Montenegro

Message

What I'm looking for

I'm dedicated to advancing AI language models through computational linguistics and fine-tuning, and I'm open to worldwide remote roles.

At Data Light, I evaluated LLM outputs for search relevance, contextual understanding, and text classification accuracy. I also checked factual correctness and safety, and wrote technical feedback in English for development teams.

I collected, annotated, and validated multilingual text and audio datasets for machine learning and language model training and fine-tuning. I designed prompts to test edge cases and probe model boundaries.

I assessed speech recordings for naturalness, pronunciation, intonation, and tempo, checking them against quality metrics for speech synthesis models. I also performed Machine Translation Post-Editing and terminology alignment using CAT tools.

My background is in Linguistics, including English and Chinese, and I bring experience in computational linguistics, dataset quality control, and model evaluation. At Data Light, I refined evaluation guidelines with project coordinators and maintained dataset metrics in MS Excel.

Experience

Work history, roles, and key accomplishments

AI Language Model Evaluator

Data Light

Jul 2025 - May 2026 (10 months)

Evaluated LLM outputs for relevance, factual accuracy, and safety; curated and annotated multilingual datasets; performed prompt engineering and MTPE; assessed speech data quality.

LLM Evaluation Prompt Engineering Data Annotation Machine Translation Post Editing CAT Tools Excel Quality Assurance Multilingual Data