The role involves building and operating safety, oversight, and intervention mechanisms to protect AI models on third-party cloud service provider platforms. The engineer will design architectures that monitor requests for misuse and ensure compliance with data residency and privacy commitments. Responsibilities include developing telemetry, logging, and evaluation pipelines to provide situational awareness over traffic. The position requires managing the deployment of real-time safeguards infrastructure directly within the inference serving path. Additionally, the role entails driving root-cause analyses and postmortems for incidents while collaborating across various internal teams and external partners.

Candidates must possess a Bachelor’s degree in Computer Science, Software Engineering, or a comparable field. A minimum of 7 years of experience in high-scale, high-reliability software development is required, specifically with trust, safety, anti-abuse, fraud, or integrity systems. Proficiency in Python and the ability to work across the full stack are necessary. Strong communication skills are essential for explaining technical and risk tradeoffs to non-technical stakeholders.