Principal ML Solutions Architect

The role sits within Nebius Token Factory, our serverless platform for running and customizing open-source LLMs in production. Token Factory enables serverless inference and fine-tuning (LoRA, full FT, RFT) with in-house optimizations like speculative decoding, quantization, cache-aware routing, and dedicated endpoints. You will be the primary technical voice shaping the platform roadmap and you will mentor other Solutions Architects. Responsibilities include owning the most complex customer engagements from architecture to production, optimizing LLM inference at framework and hardware levels, leading fine-tuning efforts, designing production-ready LLM solutions, advising on prompt engineering and cost-performance trade-offs, and partnering with product and research teams to surface customer needs and drive platform features. You will guide customers from PoC to production with a focus on performance, reliability, and cost efficiency.