Responsibilities
- Design, implement, test, and support query operators, expression evaluation, execution scheduling, runtime planning, and resource management.
- Optimize vectorized processing, concurrency, parallelism, memory usage, data exchange, and disk spilling.
- Investigate query correctness and performance issues using query profiles, profiling tools, telemetry, benchmarks, logs, and production data.
- Optimize Java and JVM CPU utilization, allocation behavior, garbage collection, thread behavior, and runtime characteristics.
- Collaborate with Query Planner, Datalake, Product, Support, and field engineering teams on end-to-end query improvements.
- Use AI-assisted tools for code comprehension, debugging, test generation, documentation, and incident analysis, validating outputs through review and testing.
- Contribute to technical direction, participate in design and code reviews, and mentor other engineers.
Requirements
- 5+ years of experience developing production software, preferably in database systems, query execution, distributed systems, or related areas.
- Strong Java programming skills; C++ experience is a plus.
- Strong foundations in data structures, algorithms, concurrency, multithreaded programming, and asynchronous programming.
- Knowledge of database internals, query processing, distributed execution, and performance optimization.
- Experience profiling and optimizing CPU, memory, garbage collection, thread behavior, or other runtime characteristics.
- Ability to solve ambiguous technical problems, evaluate tradeoffs, validate solutions rigorously, and work across team boundaries.
- Strong communication skills, ownership, and commitment to delivering high-quality software.
- Bonus qualifications include experience with distributed or database query engines, vectorized execution, query operators, expression evaluation, code generation, runtime optimization, JVM profiling, memory management, caching, networking, data exchange, execution scheduling, disk spilling, data platforms, and open-source contributions.
Tech Stack
Categories
About Dremio
Dremio is the Agentic Lakehouse: the only Iceberg-native data platform built for agents and managed by agents. Every knowledge worker and AI agent gets instant, governed access to enterprise data through any LLM or tool of their choice. Federated queries reach any source without ETL pipelines. An AI Semantic layer adds business context so every agent draws from the same source of truth. The lakehouse manages itself, running clustering, optimization, and compaction autonomously. The result: trusted insights that drive better business outcomes, without the infrastructure complexity or overhead. A lead contributor to Apache Iceberg and co-creator of Apache Arrow and Apache Polaris. Trusted by Shell, TD Bank, Michelin, and thousands of organizations worldwide. www.dremio.com