You will own the system prompts, evaluation sets, and production performance of the YOlanda AI concierge. This involves managing model routing, caching, and governance to ensure the AI remains accurate, cost-effective, and fast in a production environment.
You will own the system prompts, persona, and evaluation frameworks for the YOlanda AI concierge to ensure accurate and safe user interactions. This involves writing training data, managing the model's knowledge boundaries, and shipping code to production using LangChain and LangGraph.
Build and maintain a shared KMP core for an AI inference platform, including business logic and state machines. Design the public API and migrate existing Android and iOS native code to the shared module.
Establish and lead the QA process for the YOnC AI platform, covering mobile apps, backend consoles, and web products. Responsibilities include verifying telemetry data, sanity-checking performance benchmarks, and building test automation for repetitive tasks.
