CV
The short version is on the about page. This is the full record.
Roles
- 2026 — present
AI Training & Evaluation (Contract), Mercor
- Adversarial evaluation of frontier LLMs: designing prompts and tasks built to make strong models fail on web search, multi-step reasoning, and the edge cases where they are confidently wrong.
- Writing verified golden answers and single-answer rubrics, so that every failure found is reproducible and objectively scorable rather than a matter of opinion.
Study
B.Sc. in Computer Science
University of Guilan