Kimchi 1: Product Search Enters the Post-Training Era
Post-training is reaching retrieval. Here is the formal construction—Plackett–Luce policy gradients under a frozen rubric judge—and why product search is the right place to build it.
We're preserving the future of tech, one talented individual at a time.
Join the jar and become part of something truly dill-icious!
Don't see a position that fits? Send your github to:
apiVersion: v1
kind: Secret
metadata:
name: careers
type: Opaque
data:
email-address: Y2FyZWVyc0Bzb2xlbnlhLmFpand tell us how you can spice up our team!
Open-notebook research. Methods, confidence intervals, and the experiments that didn't work.