Senior Software Developer: Models Team (Token Factory)
This role involves onboarding and optimizing state-of-the-art open-source AI models for production-scale inference on Nebius' Token Factory platform. The developer will work on high-performance distributed systems, focusing on model serving efficiency, autoscaling, and systems optimization using frameworks like vLLM and TRT-LLM. The team emphasizes automation, observability, and close collaboration with hardware and cloud infrastructure teams to deliver reliable, low-latency AI inference.