To build automated evaluations, rater systems, and interpretability metrics that advance AI solution quality beyond the state-of-the-art. We aim to create the invisible layer powering reliable, efficient, and explainable AI.

Develop robust, automated evaluation frameworks to benchmark LLM performance on your data, ensuring reliability and accuracy.
Are you an exceptional PM/CPO or ML/Eng candidate seeking an opportunity to join a well-funded Zurich-based early-stage startup?
Send us your cv
@ 2025 Periscoop AI AG.
All rights reserved ©2025