Machine Learning, Platform Engineer

This role focuses on enabling custom models and dedicated inference on the platform, delivering high-performance end-to-end ML workflows.
You will optimize autoscaling, minimize cold starts, and improve end-to-end model performance while delivering a superb developer experience.
Responsibilities include building scalable distributed systems and API microservices, with a focus on robustness, efficiency, and fault tolerance.
You'll work on multi-cluster orchestration, predictive autoscaling, model bring-up, and tooling such as APIs, SDKs, and CLI for deployments.
You will collaborate with product teams, conduct design reviews, write well-tested code and infrastructure, and document systems for long-term maintainability.
The role demands strong low-level OS concepts, concurrency and networking knowledge, and proficiency in one or more of Go, Rust, Python, C++, or Haskell.