About this role
You will own the end-to-end AI coaching layer for a production platform, focusing on retrieval quality, prompt engineering, and building robust evaluation systems. The role involves developing assessment scoring pipelines and ensuring LLM outputs adhere to specific behavioural-science methodologies.
Skills for this role
PythonLLMQdrantRAGEmbeddingsPrompt EngineeringMachine LearningPostgreSQLEvaluation