Yuki Tanaka

Benchmark design, automated red teaming, and interpretability hooks for production chatbots in high-stakes domains.

• Published internal harm taxonomy adopted across 3 product lines
• Built multilingual jailbreak suite with monthly regression runs

1. Staff Researcher

   Slate Theory · 2020 — Present

   Staff researcher: internal harm taxonomy adopted across three product lines; quarterly exec readouts on residual risk. Multilingual jailbreak suite with monthly regression after each release train. Red-team cockpit: campaign scheduling, exploit half-life tracking, export packs for governance forums.

Contact messages are stored when DATABASE_URL is set. Run npx prisma db push and try again.