Young Jai is a software engineer with four years' experience building production-grade ML and data platforms, currently at Kakao after prior ML engineering work at AhnLab. He designs scalable inference and serving systems—authoring a Python asyncio + RabbitMQ ML serving framework, GPU-accelerated Visual Transformer inference pods (70+ TPS/pod with Triton), and Prometheus/Grafana monitoring for Kubernetes deployments. He also implements large-scale data pipelines with Spark Structured Streaming and Kafka, optimizing queries and extracting statistical features over 100M+ rows. Comfortable across model engineering, GPU-based embedding clustering, and graph/network analysis, he blends statistical training with practical systems engineering from his statistics background at Sungkyunkwan University. An interesting detail: he routinely relieves CPU image-processing bottlenecks by moving transforms into PyTorch tensors to unlock GPU throughput in production.
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.