Senior ML Solutions Architect - Token Factory
Core
Design and implement optimized inference workflows and scalable AI applications using Nebius Token Factory's serverless platform for open-source LLMs across text, vision, and audio modalities.
Role type
Senior ML Solutions Architect (LLM inference & fine-tuning)
Builds
Production-ready LLM applications and customized solutions leveraging serverless inference and fine-tuning services
Domain
Generative AI / Large Language Models / Cloud Infrastructure
Deliverable
production ML models
Required skills
LLM ecosystem knowledge, supervised and reinforcement learning fine-tuning, LLM evaluation pipelines, inference frameworks (vLLM, SGLang, TensorRT-LLM), Python programming, prompt engineering, RAG architectures
Preferred skills
Multimodal AI models, DevOps tools (Docker, Kubernetes), open-source ML/AI contributions
Technologies
vLLM, TensorRT-LLM, SGLang, Transformers, OpenAI SDK, Anthropic SDK, Kubernetes, Docker, Git, AWS SageMaker, GCP Vertex AI, Azure ML
Responsibilities
Optimize LLM inference across various modalities, provide support in supervised and reinforcement learning fine-tuning, design and implement LLM-based solutions, build production-ready applications, provide technical expertise in prompt engineering and RAG, collaborate with product and engineering teams, guide customers in scaling from POC to production
Seniority
Senior, hands-on IC
