Senior Software Developer: Models Team (Token Factory)

# Models Team – AI Infrastructure Engineer

Nebius is building a full-stack AI cloud platform. The Models Team is responsible for onboarding state-of-the-art open-source models into Nebius TokenFactory and serving large-scale AI models efficiently and reliably in production.

## Responsibilities
You will work on advanced inference and systems optimization techniques including:

• Cache-aware routing
• NUMA-aware deployments
• KV-cache offloading
• Disaggregated serving architectures
• Autoscaling with high-speed model loading over InfiniBand / RoCE

The team maintains and extends forks of leading inference frameworks such as vLLM and TRT-LLM. You'll invest heavily in tooling and automation including performance testing frameworks, hyperparameter optimization, observability tooling, and automated rollout pipelines.

You'll collaborate closely with model builders, open-source communities, Nebius Cloud teams, and hardware vendors to continuously improve serving infrastructure.

## Team
The team consists of eight engineers distributed across Europe (Netherlands, UK, Germany, Latvia). Workflows are optimized for remote collaboration with in-person meetings every one to two months.

## Technical Stack
Primarily Go and Python for building and scaling backend systems. Work sits at the intersection of distributed systems, high-performance computing, and modern AI infrastructure.