Teams at Cortea AI

Build production-grade evaluation, observability, and data infrastructure for multimodal LLM agents. Develop online and offline evaluation pipelines, golden datasets, quality gates, replay and retention systems, and trace analysis workflows. Use analytical databases to identify quality, latency, reliability, and cost issues. Operate observability and experimentation tooling while partnering with backend engineers to improve retrieval and reasoning agents.

Own the architecture, development, infrastructure, security, observability, and reliability of an AI product platform. Build shared APIs, libraries, golden paths, Kubernetes and cloud infrastructure, CI/CD, SLOs, alerts, authentication, authorization, compliance controls, and AI developer tooling. Operate distributed systems end to end, scale transactional databases, improve background processing, control infrastructure costs, and support reliable document and agent execution pipelines.

Translate ISA (UK) and international auditing standards into structured product logic and AI workflows. Develop, test, and refine prompts; ensure audit documentation, independence, ethics, and quality-control requirements are met. Collaborate closely with product and engineering teams, shape the roadmap, review prototypes, and support the development of transparent, reviewable audit technology. Regular travel between London and Berlin is required.