AI Backend Engineer (Web3)

TL;DR

AI Backend Engineer (Web3): Developing agent runtimes, intent routing, and RAG systems for a global blockchain ecosystem with an accent on tool orchestration and evaluation. Focus on optimizing tool-call efficiency, building evaluation datasets, and ensuring system observability in a production LLM-app stack.

Location: Hong Kong (Work-from-home arrangement possible)

Company

Binance is a leading global blockchain ecosystem and the world’s largest cryptocurrency exchange by trading volume and registered users.

What you will do

• Build and improve agent runtime components including intent routing, query rewrite, and RAG/FAQ answering.
• Extend and optimize the Tool Server for web search, market data, and report APIs.
• Create evaluation datasets and harnesses to measure routing accuracy and answer quality.
• Implement observability via traces, metrics, and logging using Opik and Pinpoint.
• Fix pipeline bugs and write integration tests with mock-LLM cassette replay.

Requirements

• Current university student or recent graduate.
• Strong Python skills and clean coding habits within a CI/CD environment.
• Basic understanding of LLM applications, prompting, RAG, and tool calling.
• Ability to debug across asynchronous services and write robust tests.
• Availability for a sustained 3-6 month internship.

Nice to have

• Experience with AgentScope, LangChain, or LlamaIndex.
• Familiarity with vector search, embeddings, or LLM observability frameworks.
• Exposure to Kafka, Redis, S3, Docker, or Kubernetes.
• Interest in prompt-attack defense and latency/cost optimization.

Culture & Benefits

• Opportunity to ship real features into a production AI agent used across the app.
• Mentorship from senior Backend, Data Science, and Algorithm engineers.
• Hands-on experience with a modern LLM-app stack including RAG and LLMOps.
• Competitive salary and company benefits.
• Flexible work-from-home arrangements depending on the business team.