Software Engineer, Data Systems
Core
Build advanced software tools to analyze AI workload performance across GPU data centers by managing data stores, models, and query paths.
Role type
Senior IC data systems software engineer
Builds
Advanced software tools for analyzing AI workload performance on GPU data centers
Domain
AI infrastructure / GPU data centers / High-scale data systems
Deliverable
production ML models
Required skills
C++, Python, SQL, large-scale data pipeline design, low-latency streaming, data modeling, data contract management, performance tuning, debugging across component boundaries
Preferred skills
Telemetry and time-series data experience, ClickHouse, Arrow, Parquet, profiler data formats, Go
Technologies
C++, Python, SQL, ClickHouse, Arrow, Parquet, Go
Responsibilities
Develop and construct the store, data model, and query path for engineering performance data at GPU data center scale. Join profiling data with system context (hosts, schedulers, logs). Establish, version, and transition data contracts with generating teams. Make trade-offs among data quality, latency, storage cost, and retention. Handle delayed, duplicated, or inconsistent data. Develop data APIs and access controls.
Seniority
Senior, hands-on IC
