Staff AI Engineer

Role overview A staff-level engineering position responsible for setting the technical bar across the full lifecycle of production LLM systems. The work centers on agents, retrieval-augmented generation, and evaluation infrastructure built for enterprise clients with demanding requirements. The role combines deep hands-on engineering with technical leadership that lifts the standard across the team.

Responsibilities - Define and evolve the technical direction for how production LLM systems are designed, shipped, and operated - Lead architectural decisions for agents, RAG pipelines, and evaluation frameworks targeting enterprise deployments - Establish engineering standards and best practices for reliable, production-grade AI - Guide other engineers and raise the technical quality of work across LLM-based products - Partner with client-facing teams to ensure solutions meet the expectations of demanding enterprise customers

Requirements - Extensive hands-on experience building and operating production LLM systems at scale - Deep expertise with agent architectures, retrieval-augmented generation, and evaluation methodologies - Demonstrated ability to set technical direction and lead at a senior or staff level - Track record of shipping AI systems that hold up under real production and enterprise conditions