Senior LLM Evaluation & Conversational AI Team Lead — 2 Hour/Day

We are looking for a senior conversational-AI engineer to technically lead a team of four outstanding junior developers in a selective software-engineering bootcamp. The team is building a real LLM-based application for an established high-tech company. The company name, specific user scenario, and complete product context will be disclosed only to shortlisted candidates. The technical challenge is to build an interactive LLM-based simulation and assessment system. It includes configurable personas, hidden structured ground truth, multiple behavior and difficulty levels, structured scenario authoring, automated scoring of conversations, and actionable feedback. The difficult part is not simply connecting a chat interface to an LLM. The system must behave consistently enough to support training and assessment, and it must evaluate what information the user successfully uncovered during a conversation. The developers will write the code. You will provide approximately 2 hours of hands-on technical leadership each working day, helping the team make sound architectural and evaluation decisions.