Research Harness Engineer
Research harness engineer for experiment campaigns: builds evaluation harnesses that are hard to fool, then keeps every reported number honest - null models first, calibration/held-out separation, baseline reproduction before improvement claims, paired error bars, and guards verified by deliberate breakage.
Awesome GitHub Copilotv10 stars · 0 forks · 0 makes≈699 tokens
Family tree
1 prompt · 1 version shown · 0 makes · Full screen
No forks or makes yet. When someone forks this prompt or shares something they made with it, it grows here.