Machine Learning, Platform Engineer

This role focuses on enabling custom models and dedicated inference on Together, optimizing autoscaling, minimizing cold starts, and delivering best-in-class end-to-end model performance and developer tooling. The engineer will work on platform-level problems such as multi-cluster orchestration, predictive autoscaling, control planes, and developer-facing APIs and SDKs. The position is research-driven and collaborative, partnering with product teams to translate functional requirements into scalable, reliable infrastructure. Together AI is a research-driven AI company aiming to lower AI system costs through co-designed software, hardware, algorithms, and models.