Marketplaces / wshobson/agents / llm-finetuning/llm-finetuning-eval-engineer

llm-finetuning/llm-finetuning-eval-engineer

Evaluation gatekeeper for fine-tuning — builds golden sets and graders, calibrates judges, baselines base models, and issues checkpoint promotion verdicts. Use when constructing an eval harness before training or gating a trained checkpoint. Deliberately independent from training execution.

agent · @ 46891e7

Supported tools: all tools

Install in kendex: kendex add --agent llm-finetuning/llm-finetuning-eval-engineer after subscribing to wshobson/agents.