About the role
Responsibilities Turn scenario specs and assessment rubrics into prompts, application logic and testable behavior Define how AI models connect to application services and approved data sources Design prompts, structured outputs and validation logic Build conversational runtimes with controlled personas and explicit state transitions Implement grounding and retrieval from approved knowledge sources Run bounded experiments with Product and take validated prototypes into production Help build technical controls for accreditation requirements Requirements Expert prompt and context engineering Structured outputs with JSON Schema and validation layers RAG design including chunking, hybrid search and citation grounding Agentic systems with tool use and human-in-the-loop checkpoints AI evaluation with golden datasets and rubric-based scoring LLM security including prompt injection and guardrails Python or TypeScript with API integrations and automated testing Git, reproducible tests and CI Preferred Qualifications Background in learning products, assessment, simulations or regulated professional content About the Company E-learning provider for professionals in regulated industries such as healthcare and finance, with distributed Agile teams.