Senior Software Developer: Models Team (Token Factory)
Nebius — Amsterdam, North Holland, Netherlands · Hybrid · Senior
Role description
Role Overview
The Models Team is responsible for onboarding state-of-the-art open-source models into Nebius TokenFactory. The team works on advanced inference and systems optimization techniques, including cache-aware routing, NUMA-aware deployments, and autoscaling with high-speed model loading over InfiniBand / RoCE.
What You Will Do
You will work on serving large-scale AI models efficiently and reliably in production, using advanced inference and systems optimization techniques. You will also maintain and extend forks of leading inference frameworks such as vLLM and TRT-LLM.
Why It Might Be a Fit
This role is a good fit for someone with experience serving LLMs in production, strong Python and/or Go programming skills, and experience designing and operating highly scalable, highly available distributed services.
Requirements
- Experience serving LLMs in production
- Strong Python and/or Go programming skills
- Experience designing and operating highly scalable, highly available distributed services
Benefits
- Competitive compensation
- Career growth and learning opportunities
- Flexibility and ownership
- Collaborative and innovative culture
- Opportunity to work on impactful AI projects
- International environment and talented teams