Binance Accelerator Program - Full Stack Engineer (Backend Oriented) Fully Remote

Location: Remote; applicants based in APAC, Australia, Hong Kong, Malaysia, New Zealand, Singapore, or Taiwan

Company

Binance operates a global blockchain ecosystem offering cryptocurrency trading, financial services, payments, education, research, and digital-asset products.

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 tool discovery, execution, result handling, web search, market data, and internal services.
• Develop evaluation datasets and harnesses to measure routing accuracy, answer quality, tool-use performance, and agent reliability.
• Improve agent quality through failure analysis, regression detection, prompt and workflow optimization, and guardrails.
• Build observability and reliability features using tracing, metrics, logging, dashboards, production monitoring, and integration tests.
• Collaborate with Backend, Data Science, and Algorithm engineers to 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, problem solving, and system trade-offs.
• 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 APIs, asynchronous services, testing, CI/CD, code review, and real codebases.
• Strong debugging and analytical abilities, with a focus on understanding the causes of failures.

Nice to have

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

Culture & Benefits

• Remote-first, work-from-home arrangement, which may vary depending on the role and team.
• Opportunity to ship 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 from Backend, Data Science, and Algorithm engineers in a global, user-centric organization.
• Competitive salary, company benefits, career growth, and continuous learning opportunities.