Remote LLM Engineer for Multi-Agent AI & RAG Systems

Remote; San Francisco (CA); Remote; USD 150,000 - 230,000; Full time

Job summary

Binance is seeking a highly skilled AI professional to advance innovative AI solutions, focusing on developing and refining LLMs for actionable insights and improved decision-making. The role emphasizes building scalable LLM/RAG frameworks for customer service scheduling and deploying LLM services across multi-GPU clusters, all in a 100% remote work setup.

Collaborate with product and CS teams to integrate models into conversational chatbots and contribute to cutting-edge AI research and

Qualifications

• 2+ years in deep-learning/NLP with practical LLM work.
• Experience in prompt engineering and tuning.
• Experience deploying multi-agent LLM workflows.
• Proficient in English and Chinese communication.

Responsibilities

• Own end-to-end LLM pipeline from data preparation to production.
• Design and optimize prompts for multi-language use.
• Build Retrieval-Augmented Generation (RAG) QA systems connected to multi-source knowledge bases.
• Deploy LLM services on multi-GPU or cluster environments.
• Design, implement and operate multi-agent LLM architectures with task decomposition and tool-calling workflows.
• Develop evaluation pipelines (metrics and human feedback) to measure quality, bias, and hallucination.
• Collaborate with product and CS teams to integrate AI models into conversational chatbots.
• Track cutting-edge research and publish technical blogs while improving architecture.

Skills

Prompt engineering

LLM deployment

Multi-agent workflows

NLP & DL

English & Chinese

Education

Master's Degree in CS/Data Science

Tools

vLLM

SGLang

LangGraph

CrewAI

AutoGen

Job description

Binance is seeking a highly skilled AI professional to advance innovative AI solutions, focusing on developing and refining LLMs for actionable insights and improved decision-making. The role emphasizes building scalable LLM/RAG frameworks for customer service scheduling and deploying LLM services across multi-GPU clusters, all in a 100% remote work setup.

Collaborate with product and CS teams to integrate models into conversational chatbots and contribute to cutting-edge AI research and