109 561
15 641
Astra DB is a NoSQL Database running on the Cloud, and it is internally powered by Apache Cassandra. In Astra DB we run datasets of hundreds of Terabytes of data, with super low latency, both for writes and for reads. The Astra DB Query and Storage team contributes to improve Astra DB in the following areas: - Indexing: building high performance and storage-effective indexes - Improving quering features in Cassandra - Vector Search (foundation for GenAI applications) - Disk formats (data, metadata and indexes) - Compaction and storage optimization - In-memory data structures to improve performance and reduce resources utilization - Caching and Tiered Storage You are going to be part of the Astra DB Query and Storage team, that is responsible for everything around how Astra stores and accesses data. The main goal is to improve Cassandra and Astra to make it more efficient. What you will do: - Contribute to designing and implementing new features - Improve existing code - Investigate system behavior (profiles, flamegraphs, metrics...) and provide solutions to improve efficiency or to solve performance issues - Collaborate to find the best data structures and disk formats to support existing and new features - Run and operate the software on Kubernetes and on the Cloud: while we dont work on production system directly, Astra is a based on Kubernetes and runs on all the major Clouds, so we run and test everything there - Collaborate with Production Engineering to support investigating and solving issues in production system