Remote LLM Engineer & RAG Architect
Posted Updated
Description
Binance is seeking a highly skilled AI specialist to advance through innovative AI solutions and build scalable LLM/RAG frameworks. The role focuses on extracting actionable insights, improving decision-making, and designing robust prompt systems for customer service scheduling.
This remote position leverages cutting-edge architectures and requires strong cross-language communication. The candidate will work on vLLM/SGLang based deployments, multi-GPU environments, and integration with Chatbot
Own the full LLM pipeline from data prep to production use. Design and optimize prompts for multi-language support and safety. Build Retrieval-Augmented Generation (RAG) systems across knowledge bases. Deploy LLM services on multi-GPU or cluster environments. Implement and operate multi-agent LLM architectures and tool-calling workflows. Develop evaluation pipelines using metrics and human feedback. Collaborate with product/CS to integrate AI models into chatbots. Track research and publish tech blogs; improve architecture. Master’s degree or higher in Computer Science, Data Science or related field. At least 2 years of deep-learning/NLP experience, including 1+ year LLM work. Prompt engineering & tuning expertise (few-shot design, structured prompting). Experience deploying multi-agent LLM workflows and guard-rail design. Proficient in English and Chinese for cross-team collaboration. Remote-first Competitive salary Career growth Continuous learningSkills
Sign in to read and join the discussion.