Teams at Poetiq

Build a scalable platform around foundation models and LLMs, architecting multi-step, stateful workflows and high-performance infrastructure to manage asynchronous, parallel queries and enable autonomous research.

Research and implement core algorithms for a self-improving reasoning engine. Develop data-efficient methods to probe LLMs, extract hidden knowledge, synthesize fragments into reliable answers, and design autonomous self-improvement loops. Publish and bring novel ideas to production.