"Jahnvi Singh team on AMD Developer Hackathon: ACT II Hackathon"

Team Idea

Smart LLM router that picks Gemma models by query complexity—cutting inference costs while keeping output quality. Built on Fireworks AI + AMD Cloud.

Team Members

Unknown Hacker

jahnvisingh15344387

Submission

Hybrid Token-Efficient Router

An AI agent that answers 8 different task types by routing each one to a free local model when it can, and to Fireworks only when the task genuinely needs a stronger model, cutting token usage without hurting accuracy.