Machine Learning Engineerat ScaleAI Labs

Dear ScaleAI Labs, I'm applying for the ML Engineer role. My specialty is the gap between ML research and production: I take models that work in notebooks and make them work at scale, reliably, and efficiently. At my current role, I reduced inference costs for a real-time recommendation system by 70% through model quantization and batching optimizations, while maintaining 98% of the original accuracy. I also led the migration of our training pipeline to distributed training on 64 GPUs using PyTorch DDP, cutting training time from 18 hours to 2 hours. ScaleAI Labs' focus on efficient large model deployment is exactly the problem space I find most compelling. I want to work on making powerful AI systems accessible at a cost that makes business sense. Excited to learn more, Riley Park