Data/ML/AIDevOps/CloudHigh signalEmerging
LLMOps
Also written as LLM Ops, GenAIOps, AgentOps, LLM Observability, Langfuse, Arize AI, Arize Phoenix, Helicone
The practices for running LLM-based products reliably once they're live: versioning prompts and models, logging every request, monitoring cost, speed and answer quality, and running evaluations before each change ships. The LLM-era cousin of MLOps.
Think of it like
The flight-data recorder and maintenance log for an AI product.
Junior or senior?
Separates people who shipped a demo from people who kept an AI product working for real users.
Senior sounds like
Can name a quality or cost problem they caught through monitoring and how they fixed it without breaking something else.
Ask them
“How did you know your AI feature had got worse after a change, and how quickly did you find out?”