Multilingual QA Governance and RAG Evaluation Expert for ModelsMultilingual QA Governance and RAG Evaluation Expert for Models
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Ilya's avatar
Ilya Garaeff
• May 25
I engineered multilingual QA governance and RAG evaluation systems for frontier models at Turing, optimizing personalization across 5,000+ data samples. I built a scalable training system by designing structured error taxonomies and automated debug metadata workflows. Key Architectural Results: • Model Optimization: Cut model output inconsistencies by 18% through multi-turn SxS evaluation. • Sprint Alignment: Synchronized cross-functional teams with rapid Agile RLHF deployment cycles. • Risk Management: Mitigated hallucinations by tracking semantic drift and grounding metrics.
AI Engineer Jira
Post image
Back to feed
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started