Usability Testing, metric design and validation, Data Analysis, AI model and agent mechanisms, Failure Analysis, experiment design, evaluation methods, user research methods

Python, Incident management practice, Understanding of LLM agent architectures and failure modes, Clear technical writing, Monitoring alerting and observability, Production operations experience, Evaluation methods and metric design for AI systems, LLM observability and evaluation tooling, Experience with LLM agentic systems, Log trace analysis, Dashboarding tools, Evaluation data-analysis or quality experience, Understanding of telco customer intents and journeys