The role involves designing and maintaining canonical Large Language Model APIs across on-premises and cloud environments. The individual will operate an AI gateway, managing streaming, capacity, and service level objectives. Responsibilities include implementing enterprise-grade authentication and managing API versioning, deprecation, and compatibility. The position requires integrating observability and evaluation tools to ensure system performance. Additionally, the role involves evolving software development kits and conducting performance and soak testing to enforce promotion gates.

The role requires a minimum of five years of hands-on experience with Python. Candidates must possess at least two years of experience in Large Language Model API development and testing. Additionally, two years of practical experience with GCP Vertex AI or Azure AI Foundry is necessary. No specific degree or professional qualification requirements are mentioned in the posting.