Binance Accelerator Program - Fullstack Engineer (Backend Oriented, AI)

Location: Remote in Asia

Company

Binance is a global blockchain ecosystem offering cryptocurrency trading, digital asset products, payments, institutional services, education, research, and Web3 features.

What you will do

• Build and improve Agent Runtime components, including intent routing, query rewriting, RAG, tool orchestration, and multi-step agent workflows.
• Design Tool Server and Tool Calling capabilities for discovery, execution, result handling, web search, market data, and internal services.
• Develop evaluation datasets and harnesses for routing accuracy, answer quality, tool use, and agent reliability.
• Improve agent quality through failure analysis, regression detection, prompt and workflow optimization, and guardrail evaluation.
• Strengthen observability and reliability with tracing, metrics, logging, dashboards, monitoring, integration tests, and debugging across asynchronous services.
• Collaborate with Backend, Data Science, and Algorithm engineers to experiment, benchmark, and bring AI capabilities into production.

Requirements

• Strong Python or Java programming skills and solid software engineering fundamentals.
• Strong knowledge of algorithms, data structures, and problem solving.
• Hands-on experience with LLM applications or agent systems through research, coursework, internships, or projects.
• Familiarity with RAG, Tool Calling, Function Calling, prompting, agent workflows, or LLM evaluation.
• Comfort working with codebases, APIs, asynchronous services, testing, CI/CD, and code review.
• Current university student or recent graduate eligible to participate in a 3–6 month internship program.

Nice to have

• Experience with LangGraph, LangChain, AgentScope, LlamaIndex, MCP, tool ecosystems, or agent runtimes.
• Experience building benchmark, evaluation, or LLM testing infrastructure.
• Familiarity with vector search, embeddings, RAG evaluation, or LLM observability.
• Experience with Redis, Kafka, Docker, Kubernetes, cloud-native systems, model inference, or latency and cost optimization.
• Exposure to LLM security, guardrails, prompt-injection defense, or tool-use safety.

Culture & Benefits

• Work-from-home arrangement, with the arrangement potentially varying according to the business team.
• Opportunity to ship real features to a production AI agent used by Binance users.
• Hands-on experience across Agent Runtime, RAG, Tool Calling, evaluation, LLMOps, and AI safety.
• Learning and collaboration with Backend, Data Science, and Algorithm engineers.
• Autonomy, continuous learning, career growth, company benefits, and a flat global working environment.

Hiring process

• Employment or engagement terms are determined by the contract and applicable local laws.