Tech Stack

Description

In this role, you'll collaborate with clients to design and implement customized LLM-based solutions using Nebius Token Factory's serverless inference platform. You'll build production-ready applications, guide customers from proof-of-concept to production, and work with internal teams to improve the platform based on customer needs.

Requirements

• 5+ years experience in ML/AI systems, 2+ years focused on LLMs and generative AI
• Deep knowledge of LLM ecosystem including model architectures and fine-tuning
• Hands-on experience with prompt engineering, LLM pipeline development, agentic frameworks (Langchain, Langsmith, smolagents), vector databases and RAG
• Deploying LLM-powered applications using APIs from OpenAI, Anthropic, or open-source models
• Strong Python programming skills

Responsibilities

• Design and implement LLM-based solutions using Nebius Token Factory’s inference services to drive business value
• Build production-ready applications leveraging serverless LLM APIs, including multimodal models
• Provide technical expertise in prompt engineering, RAG architectures, model selection, and inference optimization
• Collaborate with product and engineering teams to surface customer feedback and shape the platform roadmap
• Guide customers in scaling from POC to production with focus on performance, reliability, and cost efficiency