Find a jobRecruiters

多智能体协同工程师(Multi-Agent Systems & Coordination Engineer)

Exclusive opportunity

Onsite

多智能体协同工程师(Multi-Agent Systems & Coordination Engineer)

Echronos Group

多智能体协同工程师(Multi-Agent Systems & Coordination Engineer)

Skills

ReactTypescriptPythonPyTorchAI

2 months ago

Share this opportunity

Share this opportunity to other talents of your network:
✓ Offer them a visibility boost with clients.
✓ Help your contacts find their next job.

Important information


Contract type:

Permanent

Location:

Hong Kong

Work mode:

Onsite

Published on:

11 August 2026

What they need


**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)

Other offers great for you!

These companies are also looking for great profiles

AlgoviA

Ingénieur Déploiement & Intégration Systèmes Critiques

Permanent contract

Paris, France

Hybrid, Onsite

Skills

PythonSystems integrationSystem testing and validationLog analysisIncident investigationSystems and network environments

12 hours ago

Quick apply

Futurwork

Patching & Automation Specialist

Permanent contract

Belgium

Hybrid

Skills

PythonAnsibleServiceNowPatch management automationPowerShellLinux and Windows Server

10 hours ago

Quick apply

Visian

Architecte IA générative & agentique Senior

720

Freelance

Paris, France

Hybrid

Skills

AI

9 hours ago

Quick apply

The best place to find your next move

© 2026. All Rights Reserved.

Talents

Find a job

Create a profile

Solutions and tools