Sacheendra Talluri
Amsterdam, The Netherlands
I work on autoscaling stateful systems at ClickHouse. The problems I look at are when scaling is worthwhile and how to keep a fleet of autoscaling services running reliably.
Previously, I researched resource management and fault tolerance of cloud computing systems. My research explored how ecosystem capabilities shape scheduler design, which APIs workloads need beyond resource allocation, and how realistic failures affect system behavior. I earned my PhD from Vrije Universiteit Amsterdam in the Massivizing Computer Systems group.
Due to amazing collaborators, I had the opportunity to be involved in various research and engineering projects. I worked on the Kubernetes container orchestrator, tracing serverless applications, Go and JSONPath compilers, and the reliability of LLM services.
