SQL query engine for low-latency analytics on data lakehouses
CelerData operates a SQL query engine (StarRocks) optimized for petabyte-scale analytics directly on open data formats like Apache Iceberg. The tech stack reveals a distributed-systems focus: C++, Java, Kafka, Spark, and Trino alongside core database primitives. Hiring is engineering-heavy and accelerating, concentrated in performance optimization and ecosystem integration—a direct response to their documented challenges around query bottlenecks, fault tolerance, and high-availability scaling.
CelerData builds a SQL query engine designed to execute analytics workloads at scale on data lakehouses without requiring data ingestion or intermediate pipelines. The product natively integrates Apache Iceberg and operates on open data formats, positioning it as an alternative to traditional data warehouses for real-time, high-concurrency query scenarios. The company is based in Menlo Park, California, and was founded in 2022. Active development focuses on StarRocks enhancements, ecosystem integrations, and performance debugging to support growing adoption.
CelerData is a SQL query engine (powered by StarRocks) optimized for low-latency, high-concurrency analytics on petabyte-scale data lakehouses with native Apache Iceberg support.
Core stack: StarRocks, C++, Java, Apache Kafka, Apache Spark, Trino, and Parquet. Also uses Snowflake, Databricks, ClickHouse, and standard developer tools (Git, Jira, Linux).
Other companies in the same industry, closest in size