About the role
Nebius is hiring a Senior Customer AI Engineer to join its Token Factory team, helping customers move AI workloads from proof-of-concept into stable, scalable production on Nebius infrastructure. The position sits between engineering, delivery, and customer success, so you will work directly with customer engineering teams, Solution Architects, and internal Product and Infrastructure groups to make deployments reliable, performant, and cost-efficient.
Day to day, you will lead production transitions, monitor latency, throughput, cost, and reliability, and resolve bottlenecks proactively. You will also act as a trusted technical partner, handle production incidents, and feed structured insights back to product teams. The role requires practical knowledge of inference frameworks such as vLLM or TensorRT, a solid grasp of cloud, distributed systems, and AI/ML workloads, plus experience working with technical customers. Nebius welcomes remote work from Europe and offers a.
Highlights
- Remote role open to candidates based in Europe
- Focused on production AI/ML workloads, LLM inference, and GPU infrastructure
- Direct collaboration with customer engineering teams and internal product groups
- Requires hands-on inference framework knowledge such as vLLM or TensorRT
This recap is dataskew's editorial summary, not the company's copy.