The Serving Systems team is responsible for a broad range of high throughput and low latency distributed systems. These include ML feature store, ML online infra, various data intensive systems built on distributed replicated RocksDBs and HDFS. This team plays a vital role in building next generation infrastructure to power more real-time and personalized discovery experiences on Pinterest.
What you’ll do:
Build, own and improve innovative, high throughput, low latency stateful serving systems with rich data model
Build ML serving platform to do hundreds of millions of ML inferences per second with low latency
Build ML feature store
Contribute to open source technologies like RocksDB, Helix, Tensorflow, PyTorch, etc
Continually improve operability, scalability, efficiency, performance and reliability of core serving systems at Pinterest
What we’re looking for:
At least 3 years of industry experience in software engineering.
Deep expertise on building distributed systems at consumer Internet scale
Deep expertise on distributed storage and caching systems
Strong ability to work cross functionally with product teams and other infrastructure teams
Fluent in C++ and/or Java
BS/MS/PHD in Computer Science, Engineering, or a related technical discipline or equivalent experience
Pinterest is full of possibilities to design your life. Discover recipes, style inspiration, projects for your home and other ideas to try.