ML Solutions Architect

The role sits within Nebius Token Factory, our serverless platform for running and customizing open-source LLMs in production. Token Factory allows for serverless inference and fine-tuning (LoRA, full FT, RFT) backed by in-house optimizations like custom speculative decoding, quantization, cache-aware routing and dedicated endpoints. This role acts as the most senior technical authority for customers leveraging Token Factory's serverless inference and fine-tuning platforms. You will design and implement optimized inference and fine-tuning workflows, set technical direction across large accounts, own performance and quality problems end to end, mentor others, and shape the platform roadmap with backend, product, and research teams. You may work remotely from the United States. Responsibilities include: owning complex engagements from architecture to production, optimizing LLM inference, leading supervised and reinforcement fine-tuning, designing production-ready LLM solutions, providing deep technical expertise, collaborating with product/engineering/research, guiding customers from PoC to production, mentoring architects, and representing Token Factory externally. Requirements include: 8+ years ML/AI systems, 4+ years on LLMs, leadership, expert LLM knowledge, hands-on inference optimization, production experience, fine-tuning, evaluation pipelines, ability to read/modify inference libraries, deployment experience, strong Python, excellent communication. Bonus: OSS contributions, published research, multimodal AI, DevOps tooling. Preferred stack: Python, vLLM, TensorRT-LLM, SGLang, Transformers, OpenAI/Anthropic SDKs, Kubernetes, Docker, Git, AWS, GCP, Azure. Benefits include health insurance, 401(k) with match, parental leave, remote work reimbursement, disability & life insurance, and more. Base compensation range: $208,000 - $261,000 USD.