Achieving Scalability and Interactivity with Ray Serve

Tuesday, June 22, 8:45PM UTC

Jaehyun Sim (Software Engineering Manager) & Amar Shah (Cloud Architect/Infrastructure Engineer), Ikigai Labs

View Slides >>>

Creating a scalable and highly interactive data pipelining platform is a challenging task. Ikigai Labs is tackling this problem by enabling users to inject custom Python code into a traditional data pipelining platform. The challenges of such a flexible platform create non-traditional problems. Ray and Ray Serve enable solutions at scale without hurting data interactivity. We’ll explore the challenges we faced and how Ray and Ray Serve provided excellent flexibility in resolving those challenges. We will conclude with the potential of Ray Client to push the bar even further in the future.

Speakers

Jaehyun Sim

Software Engineering Manager, Ikigai Labs

Jaehyun Sim is a software engineering manager at Ikigai Labs, where he is building a highly scalable and interactive data pipelining platform for raw data. He is CNCF-certified CKA and CKAD and enjoys working with solving big data problems with cloud native approach, such as Kubernetes and AWS. He is currently working at making big data more transparent by making data pipelines both massively scalable and easily visualizable. He worked previously at Celect, Inc as Data Engineer and has undergraduate degrees in Computer Science and Statistics from UC Berkeley.

Amar Shah

Cloud Architect/Infrastructure Engineer, Ikigai Labs

Amar Shah is a cloud architect and infrastructure engineer at Ikigai Labs where he designs and builds the core infrastructure to support the company’s highly scalable dynamic data pipelining platform. His experiences range from building Kubernetes applications and scaling infrastructure with the latest developments in cloud native technologies like Rook-Ceph and Postgres Operator. He worked previously as a Software Engineer at IBM Cloud and is an alumni of Cornell Computer Science.