🛠 Tech Stack

💼 About This Role

You'll own the full LLM pipeline from data preparation to production, designing and optimizing prompts for diverse products and languages. You'll build and maintain Retrieval-Augmented Generation systems, deploy LLM services on multi-GPU environments, and collaborate on multi-agent architectures like LangGraph and CrewAI. This role offers the chance to work on cutting-edge AI at a global crypto exchange, with fully remote flexibility.

🎯 What You'll Do

• Own the full LLM pipeline from data preparation to production.
• Design, iterate and optimize prompts for various tasks and languages.
• Build and maintain RAG QA/search systems with multi-source knowledge bases.
• Deploy and operate LLM services on multi-GPU or cluster environments.

📋 Requirements

• 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 practical LLM work.
• Demonstrated prompt engineering & tuning expertise (few-shot, structured prompting, etc.).
• Proficient in both English and Chinese communication for cross-team collaboration.

✨ Nice to Have

• Experience with vLLM or SGLang inference architectures.
• Familiarity with multi-agent LLM frameworks (LangGraph, CrewAI, AutoGen).
• Track record of developing evaluation pipelines for model quality and safety.

🎁 Benefits & Perks

• 🌍 100% Remote work from home.
• 💰 Competitive compensation with token options.
• 📚 Continuous learning and career development opportunities.
• 🌐 Global team collaboration across diverse cultures.