The role involves designing and developing algorithms for generative models using deep learning techniques. The engineer will build applications powered by large language models for internal and customer-facing use cases. Responsibilities include developing and productionizing retrieval-augmented generation pipelines and optimizing agentic workflows for task automation. The position requires creating evaluation frameworks to ensure response quality, safety, and reliability. Additionally, the engineer will deploy scalable services to cloud environments and establish monitoring systems for performance in production.

Candidates must hold a bachelor's degree in Computer Science, Engineering, Machine Learning, or a related field. The role requires at least five years of experience in software, machine learning, or applied AI engineering, including two years of hands-on experience deploying generative AI systems in production. Proficiency in Python and backend development is necessary, alongside experience with orchestration frameworks and cloud platforms. Strong communication skills are required to collaborate with various stakeholders.