站点可靠性工程师
Site Reliability Engineer
Binance 是一个领先的全球区块链生态系统，是全球交易量和注册用户最多的加密货币交易所。我们凭借行业领先的安保、用户资金透明度、交易引擎速度、深度流动性以及无与伦比的数字资产产品组合，赢得了全球 100 多个国家超过 3 亿人的信任。Binance 的服务涵盖交易与金融、教育、研究、支付、机构服务、Web3 功能等。我们利用数字资产和区块链的力量，构建一个包容性的金融生态系统，以推进货币自由并改善全球人们的金融可及性。
职责
- 代理 RAG 与工程：设计和运营下一代检索流程 —— 超越静态的一次性检索模式，实现自适应、自我纠正和多跳检索工作流；构建具有动态检索控制、查询分解、迭代检索-反思-优化循环和多代理检索协作的代理 RAG 系统
- 前沿能力整合：与研究人员和工程师深入合作，定义并实现基于模型能力的创新 —— 包括上下文管理、长期记忆、子代理和多代理架构、自我进化代理以及现实世界任务执行
- 基准测试与评估：提出领域和 RAG 领域的基准测试和评估方法；构建基准数据集，定义标注策略，并系统地衡量和提升跨领域的代理智能 —— 包括检索效率、延迟、依据性以及任务成功率
- 现实反馈循环：利用多渠道用户反馈和现实任务数据作为主要研究信号；设计实验和数据集，持续改进生产场景中的代理和检索性能
要求
- 2-8+ 年在生产环境中使用 LLM、RAG 和 AI 代理系统的实际经验
- RAG 与代理 RAG 工程：具备从头到尾构建生产检索流程的实际经验 —— 嵌入模型（BGE、OpenAI 等）、向量存储（Qdrant、Milvus、Pinecone、Weaviate）、混合搜索（关键词 + 向量）、重排序模型；对分块策略、文本清理和多模态数据解析有深入理解；有实现代理 RAG 模式的经验 —— 自我 RAG、修正 RAG、自适应检索、多跳分解、检索-反思-优化循环
- 代理能力整合工程 —— 具备 Age
查看英文原文
Binance is a leading global blockchain ecosystem behind the world’s largest cryptocurrency exchange by trading volume and registered users. We are trusted by 300+ million people in 100+ countries for our industry-leading security, user fund transparency, trading engine speed, deep liquidity, and an unmatched portfolio of digital-asset products. Binance offerings range from trading and finance to education, research, payments, institutional services, Web3 features, and more. We leverage the power of digital assets and blockchain to build an inclusive financial ecosystem to advance the freedom of money and improve financial access for people around the world.
Responsibilities
- Agentic RAG & Engineering: Design and operate next-generation retrieval pipelines — moving beyond static retrieve-once patterns to adaptive, self-correcting, and multi-hop retrieval workflows; architect Agentic RAG systems with dynamic retrieval control, query decomposition, iterative retrieve-reflect-refine loops, and multi-agent retrieval collaboration
- Frontier Harness: Collaborate deeply with researchers and engineers to define and implement model-capability-driven innovations — including context management, long-term memory, subagent and multi-agent architectures, self-evolving agents, and real-word task execution
- Benchmarking & Evaluation: Propose harness-domain and RAG-domain benchmarks and evaluation methodologies; construct benchmark datasets, define annotation strategies, and systematically measure and improve agent intelligence across domains — including retrieval efficiency, latency, groundedness, and task success rate
- Real-world Feedback Loops: Leverage multi-channel user feedback and real-world task data as primary research signals; design experiments and datasets to continuously improve agent and retrieval performance in production scenarios
Requirements
- 2-8+ Year hands-on experience with LLM, RAG and AI agent systems in production
- RAG & Agentic RAG Engineering: Hands-on experience building production retrieval pipelines end-to-end — embedding models (BGE, OpenAI, etc.), vector stores (Qdrant, Milvus, Pinecone, Weaviate), hybrid search (keyword + vector), reranking models; deep understanding of chunking strategy, text cleaning, and multimodal data parsing; experience implementing Agentic - RAG patterns — Self-RAG, Corrective RAG, adaptive retrieval, multi-hop decomposition, retrieve-reflect-refine loops
- Agent Harness Engineering — hands-on experience with Agent Harness runtimes (Pi Agent, AgentScope 2.0 or equivalent orchestration frameworks): session recovery, sandbox isolation, middleware/hook systems, multi-tenant runtime, plan/execute loops, and retrieval-grounded tool calling
- LLM & Agent Fundamentals: Deep familiarity with LLM and agent mechanisms — LLM APIs, KV Cache, Agent Loop, Tool Use, Reasoning, Planning, Skills, MCP, Memory, Subagent, Multi-Agent; strong grasp of Prompt Engineering, Context Engineering
- Independent Research Capability: Can analyze ambiguous problems from first principles, generate original ideas, and drive research from 0 to 1; able to rapidly translate ideas into runnable prototypes with tight experiment iteration loops
- Heavy Agent User: Power user of agent products (coding agents, general-purpose agents); agent tools are already integrated into your daily work and life; you have taste and judgment about model behavior
- AI-native Engineering: Proficient in vibe coding — ships fast using AI-assisted workflows across unfamiliar languages, frameworks, and domains; strong learning velocity in software development
Why Binance
• Shape the future with the world’s leading blockchain ecosystem
• Collaborate with world-class talent in a user-centric global organization with a flat structure
• Tackle unique, fast-paced projects with autonomy in an innovative environment
• Thrive in a results-driven workplace with opportunities for career growth and continuous learning
• Competitive salary and company benefits
• Work-from-home arrangement (the arrangement may vary depending on the work nature of the business team)
Binance is committed to being an equal opportunity employer. We believe that having a diverse workforce is fundamental to our success.
By submitting a job application, you confirm that you have read and agree to our Candidate Privacy Notice.
Originally posted on Himalayas