Senior ML Solutions Architect - Token Factory

What this role involves

Nebius is hiring a Senior ML Solutions Architect for Token Factory, a serverless platform for open-source LLMs. The role involves optimizing inference workflows, designing LLM-based solutions, and guiding customers from POC to production. The position is remote in the US.

Skills this posting asks for

• llm
• inference
• fine-tuning
• lora
• rag
• prompt engineering
• multimodal
• serverless
• python
• pytorch
• model serving
• cloud
• speculative decoding
• quantization
• cache-aware routing
• open-source llm
• reinforcement learning
• dedicated endpoints
• poc to production
• performance optimization
• cost efficiency

Requirements

• 5 years of experience
• Level: senior
• Remote policy: remote

From the employer’s posting

About Nebius: Nebius is leading a new era in cloud infrastructure for the global AI economy. We are building a full-stack AI cloud platform that supports developers and enterprises from data and model training through to production deployment, w…