Divisional Artificial Intelligence Engineer III

Sobre el puesto

## Responsibilities • Own architecture, implementation, and operational health for a platform domain such as agent lifecycle and state, sandbox context exchange, model orchestration, or tracing and evaluation • Design services and interfaces supporting long-running tasks across deployments, restarts, retries, inspection, and replay, with durability and failure recovery • Establish reusable patterns for context packaging and retrieval across execution environments, including boundaries for access, retention, and data movement • Build or evolve model routing and orchestration capabilities; define and use measurements for quality, latency, reliability, and cost per task • Lead technical discovery with product teams, identify common needs, and prioritize platform work that reduces duplicated engineering and unplanned interruptions • Define domain-level testing, tracing, evaluation, and operational readiness practices; review production signals and lead resolution of complex incidents • Produce architecture documentation and migration guidance enabling engineers to adopt platform capabilities without extensive one-to-one support • Mentor engineers, review designs and code, and contribute to technical planning across the AI engineering group • Perform duties in accordance with company policies, procedures, and applicable federal, state, and local laws • Perform other duties as assigned ## Requirements • Bachelor's Degree in Computer Science, Software Engineering, a related technical field, or equivalent combination of education and work experience • Five (5) or more years of software engineering experience, or equivalent practical experience, including ownership of production services • Experience building LLM-powered applications or AI infrastructure • Advanced proficiency in TypeScript and/or Python and experience designing production services and APIs • Knowledge of distributed systems, asynchronous job processing, persistence, observability, cloud deployment, and secure system design • Experience shipping and supporting LLM features, including practical tradeoffs among model behavior, latency, and cost • Ability to lead technical work from ambiguous problem definition through design, implementation, rollout, and operational improvement • Ability to make platform interfaces reusable and understandable across teams with different product needs • Ability to influence technical decisions, communicate risk and tradeoffs, and mentor engineers across experience levels

Publicada el 6 nov 2026