YuanBo Li
GenAI Specialist Solution Architect @ AWS
Focused on LLM inference optimization, AI application platforms, and retrieval-augmented generation
Research
LLM Inference 2025 – present
Best practices for deploying open-source LLMs (DeepSeek, etc.) on AWS. Performance benchmarking of inference engines (SGLang) across GPU instance types including next-gen B200.
GenAI Platform - Dify on AWS 2024 – 2025
Dify Top Contributor. Building the AWS ecosystem within Dify, making Bedrock the best-supported model provider. Enabling 5 categories of SageMaker-deployed GenAI models to integrate with Dify.
LLM Translation 2024 – 2025
Best practices for LLM-based translation: terminology mapping, RAG optimization, fine-tuning, and workflow orchestration. Published a technical whitepaper at AWS Shanghai Summit 2025.
- Code aws-samples/rag-based-translation-with-dynamodb-and-bedrock
- Paper AWS Intelligent Translation Innovation and Practice in the Generative AI Era
- Talk No-Code LLM Fine-Tuning with LLaMA Factory
- Blog Implementing LLM Translation with Terminology Mapping on AWS
- Blog LLM Fine-Tuning for Translation Quality Detection (Part 1)
- Blog LLM Fine-Tuning for Translation Quality Detection (Part 2)
- Blog Building a No-Code Model Fine-Tuning Platform with SageMaker and LLaMA-Factory
RAG (Retrieval-Augmented Generation) 2023 – 2024
Primary maintainer of the GCR RAG knowledge Q&A solution. Built a multi-tenant demo platform supporting 54 Account SAs.
- Code aws-samples/private-llm-qa-bot
- Talk Best Practices and Pitfalls for Building GenAI Apps with RAG
- Blog Knowledge QA in Practice – Knowledge Base Construction (Part 1)
- Blog Knowledge QA in Practice – Knowledge Base Construction (Part 2)
- Blog Knowledge QA in Practice – Retrieval Optimization (Part 1)
- Blog Knowledge QA in Practice – Retrieval Optimization (Part 2)
- Blog Automated RAG Evaluation with TruLens
- Blog Integrate Sparse and Dense Vectors to Enhance Knowledge Retrieval in RAG
Book Translation
- Generative AI on AWS (Chinese edition), Douban 8.8/10, Co-translator, 2024 Influential Translator Award