Jobs at White Circle

Conduct end-to-end adversarial testing of LLM-powered systems, including jailbreaks, prompt injection, data leakage, tool misuse, and policy bypasses. Automate attacks with Python, build reusable attack libraries and regression tests, document reproducible security findings, and translate model failures into product requirements and customer-facing evidence. Support demos, security reviews, and sales conversations while tracking emerging AI security techniques.

Own developer relations for an AI safety platform by leading technical launches, creating content, organizing hackathons and meetups, growing open-source communities, and building partnerships with AI labs and developer tool companies. The role also contributes to promotional videos, tracks adoption metrics, and engages engineers and AI researchers across technical channels.

Provide high-touch executive support: manage calendars, inboxes, and travel; research and book services; perform operational and administrative tasks; organise information and reduce day-to-day friction in a fast-moving, async environment. Bilingual English/French required.