Oana Balmau

Oana Balmau is an Assistant Professor in the School of Computer Science at McGill University, where she leads the Data-Intensive Storage and Computer Systems Laboratory (DISCS Lab). She also holds a status-only appointment at the University of Toronto and serves as a working group chair for MLPerf Storage. Her research focuses on creating storage infrastructure that enables fast and energy-conscious insights from data, with particular emphasis on storage and persistent memory technologies for machine learning, data science, and edge computing workloads.

Dr. Balmau's research interests span computer systems, with specific focus on:

• Design and implementation of efficient key-value stores
• Storage systems for machine learning workloads
• Edge computing infrastructure
• Persistent memory technologies
• Performance optimization of data-intensive systems

Her recent work has led to significant contributions in storage benchmarking through the MLPerf Storage benchmark and in edge computing frameworks. The MLPerf Storage benchmark has become an industry standard for evaluating storage performance in machine learning environments, while her work on hierarchical edge computing addresses security and performance challenges in distributed edge environments. Her publications show consistent high-impact contributions to top systems venues, with recent work focusing on processing-in-memory virtualization, stream processing reconfiguration, and efficient data preprocessing pipelines.

Dr. Balmau has received numerous awards for her research, including:

• SEC 2024 Best Paper Award for "Falcon: Live Reconfiguration for Stateful Stream Processing on the Edge"
• MLCommons Hero Award 2023 for leadership as MLPerf Storage working group chair
• ACM SIGOPS Dennis M. Ritchie Doctoral Dissertation Award 2021 Honorable Mention
• CORE John Makepeace Bennett Award 2021 for the best Computer Science doctoral dissertation in Australia and New Zealand
• USENIX ATC 2019 Best Paper Award for "SILK: Preventing Latency Spikes in Log-Structured Merge Key-Value Stores"

As an educator, Dr. Balmau teaches courses on advanced computer systems, operating systems, and principles of computer systems design at McGill University. She has served on program committees for top systems conferences including SOSP, SIGMOD, FAST, and EuroSys, and has co-organized workshops on resource-efficient machine learning and edge computing.

She leads the DISCS Lab, which focuses on two main research directions: Systems for ML (including the MLPerf Storage benchmark) and Edge computing (including frameworks for fast and secure edge computing in hierarchical edge environments).