The role involves designing, developing, and scaling applications powered by large language models from the initial prototype stage through to production. The engineer will build backend services and APIs to support various artificial intelligence features. Responsibilities include orchestrating language models, developing agentic workflows, and implementing retrieval-augmented generation architectures. The position requires managing performance, latency, and cost efficiency for production systems. Additionally, the engineer will collaborate across multiple teams to establish best practices and standards for delivery.

The role requires a strong software engineering foundation with production backend experience using Python. Candidates must have hands-on experience building and shipping products enabled by large language models. Proficiency in API design, including authentication and error handling, is necessary. Furthermore, the position requires practical experience with agentic AI systems, retrieval-augmented generation, and vector database management.