The role involves building and improving production systems within an agent lab focused on natural language understanding. Engineers will contribute to the evolution of an AI assistant platform by working on agent orchestration, latency optimization, and memory systems. The position requires implementing frontier AI algorithms and architectures to ensure reliability at scale. Responsibilities include writing robust, extensible, and performant code while collaborating with cross-functional teams. The work focuses on enhancing product capabilities through machine learning and large language models to deliver value to enterprise customers.

Candidates must have zero to two years of experience designing and building production systems at scale. The role requires the ability to communicate clearly regarding complex engineering problems and a commitment to operational excellence. Proficiency in Python, Golang, or Java is necessary for development. Applicants should demonstrate a high level of ownership, attention to detail, and a desire to work in a fast-paced environment.