AI Production Engineer - Token Factory (Remote Europe)

Nebius Group; United States; On-site; USD 150,000 - 230,000; Full time

Benefits offered by this job

Remote work from Europe

International environment

Job summary

Nebius is seeking a Senior Customer AI Engineer to join the Token Factory team. You will guide customers from PoC to production, ensuring deployments are stable, scalable, and cost-efficient on Nebius infrastructure.

You will work with customer engineering teams, solution architects, and product/infrastructure teams to deliver reliable AI workloads, optimise performance, and drive value in production across global engagements.

Qualifications

• Technical background.
• Practical knowledge of inference frameworks (e.g. vLLM, TensorRT, or similar).
• Solid understanding of cloud or infrastructure systems and AI/ML workloads (LLMs, inference).
• Ability to troubleshoot and reason about system performance.
• Experience working with technical customers (engineers, ML teams).
• Ability to communicate complex topics clearly and effectively.
• Ownership & execution mindset.
• Strong sense of ownership – drive outcomes, not just tasks.
• Ability to manage multiple customers and priorities.
• Experience with GPU workloads or AI infrastructure.

Responsibilities

• Own the production journey.
• Lead the transition from PoC to production.
• Ensure customer workloads are deployed, stable, and scalable.
• Drive time-to-production and time-to-value.
• Ensure technical success in production.
• Understand customer architectures and use cases.
• Monitor and improve performance, cost efficiency, and reliability.
• Identify and resolve bottlenecks proactively.
• Act as a trusted technical partner.
• Work directly with customer engineering teams.
• Provide guidance on best practices and optimisation.
• Translate technical challenges into actionable solutions.
• Manage risks and incidents.
• Act as a primary technical contact for production issues.
• Coordinate with internal teams to resolve incidents.
• Communicate clearly during high-pressure situations.
• Drive continuous improvement.
• Identify opportunities to optimise and expand usage.
• Provide structured feedback to Product and Infrastructure teams.
• Help shape better solutions based on real customer needs.

Skills

Technical background

Inference frameworks

Cloud infrastructure

AI/ML workloads

Troubleshoot performance

Customer-facing experience

Communication

Ownership

GPU workloads

SRE/solutions engineering

Tools

vLLM

TensorRT

Job description

Nebius is seeking a Senior Customer AI Engineer to join the Token Factory team. You will guide customers from PoC to production, ensuring deployments are stable, scalable, and cost-efficient on Nebius infrastructure.

You will work with customer engineering teams, solution architects, and product/infrastructure teams to deliver reliable AI workloads, optimise performance, and drive value in production across global engagements.