Summary

The senior software developer will build and operate production systems for serving large-scale open-source llms through Nebius Token Factory. The role focuses on Go and Python backend development, inference optimization, distributed systems, and automated tooling, with remote collaboration across Europe and in-person team meetings every one to two months.

Responsibilities

• Serve open-source llms in production
• Design scalable distributed backend services
• Optimize inference performance and model serving
• Maintain vllm and trt-llm forks
• Build testing and diagnostics tooling
• Automate inference framework rollout pipelines
• Support demanding customer proof-of-concepts