Model evaluation

model-evaluation · Machine learning, LLMs and agents · responsibility

Also known as: evaluation, model evaluation, evals, evaluation pipelines, evaluation harness, evaluation systems, evaluation workflows, evaluate, evaluation frameworks, evaluators.

The lesson for this

• Evaluating LLM and agent systems
• Model evaluation: regression suites and release gates

Pathways that reach it

• AI forward deployed engineer
• MLOps / ML platform engineer