🎁 Before you apply, rehearse this interview. Create your free WorkMundi account and get an Interview Training on HelpsYouSpeak — no cost, no card. I want my training →
部门： AI智能体研究中心 地点： 香港, 深圳 工作经验： 实习生、应届生 招聘人数： 10人 关于岗位 我们正在寻找多智能体协同工程师，加入 echOS Agent Core 团队。 你将直接参与设计与实现： 多业务 Agent 的角色划分与职责边界 跨 Agent 状态同步与数据一致性 Agent 间协商、冲突解决与联合决策机制 多 Agent 在真实交易系统中的稳定运行 这是多智能体系统在真实产业场景中的工程化落地，而不是仿真环境中的理论实验。 ⸻ 工作重点（Focus） 你将负责构建 echOS 多智能体协同基础设施，包括但不限于： Agent 架构层 设计多 Agent 的角色模型（定价 / 库存 / 履约 / 渠道 / 计划） 构建 Agent 生命周期管理（启动、暂停、恢复、重组） 定义 Agent 权限边界与职责分离机制 协同与决策层 实现 Agent 间通信协议与状态广播 构建冲突检测与协商框架（如价格 vs 库存、时效 vs 成本） 支持集中式 + 分布式混合决策 引入多智能体强化学习（MARL）优化整体系统收益 系统工程层 构建多 Agent 仿真与回放环境 实现协同行为可观测系统（决策链路、责任归因、效果评估） 搭建 A/B 框架评估协同策略 支持新 Agent 快速接入现有系统 ⸻ 理想经验 有复杂系统 / 分布式系统 / Agent 系统经验 熟悉 Python 理解强化学习或博弈论基本概念 能将复杂业务拆解为多个自治模块 具备系统级抽象能力 加分项： Multi-Agent RL 博弈论 / 机制设计 调度系统 / 资源分配系统 企业级系统架构经验 ⸻ 你将面对的真实问题 定价 Agent 提高利润但导致库存积压，库存 Agent 要求降价清仓，如何设计可学习的协商机制？ 履约 Agent 为追求交付时效提高物流成本，如何让多个 Agent 自动达成成本与体验平衡？ 新接入一个业务模块（例如促销 Agent），如何快速融入既有协同网络？ 多 Agent 各自局部最优导致整体系统退化，如何设计全局激励？ 企业策略变化（例如从增长导向转向利润导向），如何让 Agent 网络快速重构行为模式？ ⸻ 技术栈 Python / PyTorch 分布式系统 多 Agent 框架 Typescript / React（内部工具） Department: AI Agent Research Center Location: Hong Kong, Shen Zhen Work Experience: Graduate / Early Career Number of openings: 10 About the Role We are seeking Multi-Agent Systems & Coordination Engineers to join our Agent Core team. You will help design and implement systems where multiple autonomous agents: •Share state and communicate •Negotiate resources and objectives •Resolve conflicts •Execute distributed decisions •Form stable long-term cooperation strategies This is multi-agent engineering in real industrial environments — not simulated grids. ⸻ Focus Agent Architecture •Design agent roles (pricing, inventory, fulfillment, channel, planning) •Implement agent lifecycle management (start, pause, recovery, reconfiguration) •Define responsibility boundaries and permissions Coordination & Decision Layer •Build inter-agent communication protocols •Implement conflict detection and negotiation frameworks •Support hybrid centralized + decentralized decision making •Apply multi-agent reinforcement learning to optimize global outcomes •Enable joint planning across agents Systems Engineering •Build multi-agent simulation and replay environments •Develop observability tools for coordination behaviors and decision chains •Implement A/B frameworks for evaluating coordination strategies •Enable fast onboarding of new agents into existing ecosystems ⸻ Ideal Experience •Experience with complex systems, distributed systems, or agent architectures •Strong Python •Understanding of reinforcement learning or game theory fundamentals •Ability to decompose complex domains into autonomous components •Strong system-level abstraction skills Nice to have: •Multi-Agent RL •Game theory / mechanism design •Scheduling or resource allocation systems •Enterprise-scale system architecture ⸻ Typical Problems You’ll Work On •Pricing agents increase margin but cause inventory buildup — how should agents negotiate? •Fulfillment agents optimize delivery speed at higher cost — how do agents learn balanced strategies? •A new business agent is introduced — how does it integrate into the existing coordination network? •Local agent optimization degrades global performance — how do we design global incentives? •Enterprise strategy shifts (growth → profitability) — how do agents rapidly realign? ⸻ Tech Stack Python / PyTorch Distributed systems Multi-agent frameworks TypeScript / React (internal tools)
Here's how to pick the right one and stand out in your application.
144.883Jobs
31.687IN
81%EN
That number is real. WorkMundi's database shows 144,883 open engineer roles across the world. India has the most with 31,687 jobs, followed by the United States with 30,084. If you just finished reading one job ad and felt paralyzed by choice, you're not alone—but this scale is actually an advantage. It means you can afford to be selective.
Start by geography and language. The majority of engineer ads—117,837 of them—have the job posting text written in English. Use that as one filter, but remember: the ad text language tells you nothing about whether the role actually requires you to speak English day-to-day. Read the job description carefully. Then check which countries have the volume you're targeting. Singapore, Poland, and Australia round out the top five after India and the US.
Next, learn who's hiring. Accenture has posted 2,801 engineer roles. andurilindustries, speechify, and jobgether are also actively recruiting. If you're applying to one of these names, research their hiring patterns and interview style before you apply. That homework pays off.
When you interview, expect the question every engineer hears: 'Tell me about a time you had to debug a problem that wasn't in your job description.' Have a specific story ready—not a general one. Name the tools, the deadline pressure, and what you learned. Hiring managers listen for whether you see problem-solving as part of the role itself, not a favour.