The role involves architecting multi-product AI systems, including the design of APIs, data flows, cloud infrastructure, and security protocols. The individual will design shared AI service layers such as OCR, NLP, embeddings, and document parsing. Responsibilities include driving LLM, RAG, and agent pipeline design, alongside prompt engineering and model evaluation. The position requires bridging research proofs of concept into production-grade, deployable services. Additionally, the role entails owning CI/CD pipeline health, maintaining code quality standards, and managing the pull request review process. The individual will also mentor engineers through code reviews and architecture discussions.

The role requires at least five years of experience in software engineering, including two years leading AI or machine learning projects. Candidates must possess hands-on experience building LLM and RAG pipelines in production environments. Proficiency in cloud AI services, multi-service architectures, and agent frameworks is necessary. Furthermore, the position requires strong development skills, API design fundamentals, and a proven track record of mentoring engineers and running sprints.