Healthcare · Quri AI
Optimizing AI accuracy for clinical research
We optimized Quri's machine learning infrastructure, fine-tuned their clinical research models, and implemented advanced caching strategies.
94.7%
AI model accuracy
Up from 78% baseline
73%
Faster inference
Average response time reduction
Quri AI - AI Automated Study Pipeline
The challenge
Quri's automated study pipeline depends on model output researchers can trust. The models were sitting at a 78% accuracy baseline, and inference was slow.
What we built
- ✦Fine-tuned the clinical research models against Quri's study data
- ✦Reworked the ML infrastructure behind the automated study pipeline
- ✦Added caching to cut repeated inference work
Stack
PythonLLMsML infrastructureCaching
Building in a regulated space?
Send us an email and we'll walk you through how we'd approach it.
Email us