Engineering Manager, Agent Orchestration
San Francisco · 全职 · 工程与基础设施
需要对标的能力
大模型原理 · LLM 基础Agent · 智能体设计工具调用 · Function Calling多 Agent 协作Agent 工程 · Harness / 脚手架成本优化 · 性能调优评测 · Eval 方法论AI 安全 · Prompt 注入防御AI 工程设计模式
岗位职责与要求
About Decagon
Decagon is the leading conversational AI platform empowering every brand to deliver concierge customer experiences.
Our technology enables industry-defining enterprises like Avis Budget Group, Block’s Cash App and Square, Chime, Oura Health, and Hunter Douglas to deploy AI agents that power personalized, deeply satisfying interactions across voice, chat, email, SMS, and every other channel.
We’re building a future where customer experiences are being redefined from support tickets and hold music to faster resolutions, richer conversations, and deeper relationships. We’re proud to be backed by world-class investors who share that vision, including a16z, Accel, Bain Capital Ventures, Coatue, and Index Ventures, along with many others.
We’re an in-office company, driven by a shared commitment to excellence and velocity. Our values — Just Get It Done, Invent What Customers Want, Winner’s Mindset, and The Polymath Principle — shape how we work and grow as a team.
About the Team
The Agent Orchestration team builds the runtime and model orchestration layer that powers Decagon’s agents in production. This is the orchestration layer that turns workflows, tools and guardrails into a reliable, low-latency, and delightful experience for end users.
At the core of this work is the agent harness: the routing, execution logic, tool orchestration, and control-plane systems that determine how an agent behaves in a live conversation. The team owns the full execution lifecycle of each conversation—from selecting workflows and orchestrating multiple models (e.g., router/planner/supervisor patterns), to coordinating tool calls, enforcing safety constraints, and communicating back to the user.
The team operates across both real-time systems (e.g., voice interactions with strict latency requirements) and longer-horizon execution (supporting more complex reasoning and workflows). Our research shows that an agent’s task execution reliability increasingly depends on the orchestration layer that wraps around it.
This is highly experimental, frontier-style engineering. The team continuously analyzes real-world failures, builds feedback loops through offline evaluation and online experimentation, and iterates quickly to improve quality, reliability, and capability. As model capabilities evolve, the team regularly rethinks system design to push agent performance forward in production.
About the Role
We’re looking for an Engineering Manager to lead the Agent Orchestration team. This is a highly technical, player/coach leadership role at the core of Decagon’s product. You’ll lead the team responsible for the runtime and control plane that powers every agent interaction—coordinating model reasoning, tool use, and evaluation in production—and own the technical strategy and delivery for the orchestration engine behind every customer conversation.
You’ll hire and develop a high-performing team while staying close to architecture, debugging, and reliability. You’ll partner closely with Research, Infrastructure, Product Engineering, and Agent SWE to translate frontier model improvements into predictable, safe, and scalable agent behavior in real customer environments. Success requires strong people leadership, clear execution in ambiguous problem spaces, and the technical depth to drive correctness and operational excellence.
In this role, you will
- Build, lead, and develop a high performing team of engineers, including hiring, coaching, and performance management.
- Own the technical strategy and roadmap for Decagon’s orchestration engine, balancing speed of iteration with correctness and safety.
- Drive architecture for systems that coordinate complex reasoning and action flows at scale.
- Set reliability, testing, and observability standards across the orchestration stack, and build an operating cadence that prevents repeated incidents.
- Create frameworks and guardrails that enable fast, safe iteration on agent behavior, evaluation, and rollout.
- Partner with Product, Research, and Infrastructure teams to define requirements, navigate tradeoffs, and ship multi-quarter initiatives that move core company metrics.
Your background will look something like this
- Have 2+ years of engineering management experience leading high performing teams in fast-moving environments.
- Have strong technical depth and an IC foundation that enables you to guide architecture, debug complex failures, and make sound trade-offs.
- Have experience building distributed systems, execution engines, real-time platforms, or other high scale systems where correctness and reliability matter.
- Have a track record of delivering multi-quarter projects through ambiguity, creating clarity for your team and stakeholders.
- Care deeply about engineering craft and operational excellence, including testing strategy, observability, and incident learning.
- Communicate clearly and collaborate well across Product, Research, and Infrastructure teams.
Even better if you have
- Experience with agent frameworks, runtimes, orchestration logic, or tool use systems.
- Experience with evaluation, experimentation, or model quality measurement systems.
- Experience building guardrails for safety-critical or highly reliable systems.
Compensation
$280,000 - $430,000 + Offers Equity
Benefits
We proudly offer the following benefits for our full-time employees:
- Medical, Dental, and Vision benefits for you and your family
- Life Insurance and Disability Benefits
- Retirement Plan (e.g., 401K, pension)
- Parental Leave
- Fertility and family building benefits through Carrot
- Monthly stipend to support your wellness, lifestyle, and work-life balance
- Daily lunches and snacks in the office to keep you at your best
- Take what you need vacation policy (subject to local requirements; UK employees receive 25 days of statutory leave)
Decagon offers a competitive benefits package that varies by country and complements local statutory benefits. Details for this location will be provided during the recruitment process.
查看中文参考译文
关于 Decagon
Decagon 是领先的对话式 AI 平台,赋能每个品牌提供礼宾级客户体验。
我们的技术使行业标杆企业如 Avis Budget Group、Block 旗下的 Cash App 和 Square、Chime、Oura Health 以及 Hunter Douglas 能够部署 AI agent,在语音、聊天、邮件、SMS 及所有其他渠道上实现个性化、深度令人满意的交互。
我们正在构建一个客户体验被重新定义的未来——从 support tickets 和 hold music 转向更快的解决、更丰富的对话和更深的关系。我们很荣幸得到世界级投资者的支持,他们认同这一愿景,包括 a16z、Accel、Bain Capital Ventures、Coatue 和 Index Ventures 等。
我们是一家要求到岗办公的公司,以追求卓越和速度为共同驱动力。我们的价值观——Just Get It Done、Invent What Customers Want、Winner's Mindset 和 The Polymath Principle——塑造着我们的工作方式和团队成长。
关于团队
Agent Orchestration 团队构建支撑 Decagon agent 生产运行的 runtime 和 model orchestration 层。这一 orchestration 层将 workflows、tools 和 guardrails 转化为对终端用户而言可靠、低延迟且愉悦的体验。
这项工作的核心是 agent harness:routing、execution logic、tool orchestration 以及 control-plane 系统,它们决定 agent 在实时对话中的行为方式。该团队拥有每次对话的完整执行生命周期——从选择 workflow 和 orchestrating 多个模型(例如 router/planner/supervisor 模式),到 coordinating tool calls、enforcing safety constraints,再到向用户回传信息。
该团队同时运营 real-time systems(例如具有严格延迟要求的语音交互)和 longer-horizon execution(支持更复杂的 reasoning 和 workflows)。我们的研究表明,agent 的任务执行可靠性越来越依赖于围绕它的 orchestration 层。
这是高度实验性的、前沿风格的工程。团队持续分析真实世界的 failures,通过 offline evaluation 和 online experimentation 构建 feedback loops,并快速迭代以提升质量、可靠性和能力。随着 model capabilities 的演进,团队定期重新思考系统设计,以在生产环境中推动 agent performance 向前发展。
关于职位
我们正在寻找一位 Engineering Manager 来领导 Agent Orchestration 团队。这是 Decagon 产品核心上一个高度技术性的 player/coach 领导角色。你将领导负责 runtime 和 control plane 的团队,它驱动每一次 agent 交互——coordinating model reasoning、tool use 和 production 中的 evaluation——并负责每一次客户对话背后 orchestration engine 的技术策略和交付。
你将招聘并培养一支高绩效的工程师团队,同时深入参与 architecture、debugging 和 reliability。你将与 Research、Infrastructure、Product Engineering 和 Agent SWE 紧密合作,将前沿 model improvements 转化为真实客户环境中可预测、安全且可扩展的 agent behavior。成功需要强有力的人员领导、在模糊问题空间中的清晰执行,以及推动 correctness 和 operational excellence 的技术深度。
在这个角色中,你将
- 组建、领导并培养一支高绩效的工程师团队,包括招聘、coaching 和绩效管理。
- 负责 Decagon orchestration engine 的技术策略和路线图,在迭代速度与正确性、安全性之间取得平衡。
- 为大规模协调复杂 reasoning 和 action flows 的系统驱动架构设计。
- 为整个 orchestration stack 设定可靠性、测试和可观测性标准,并建立能防止重复事故的运营节奏。
- 创建 frameworks 和 guardrails,以实现对 agent behavior、evaluation 和 rollout 的快速、安全迭代。
- 与 Product、Research 和 Infrastructure 团队合作定义需求、权衡取舍,并交付能推动核心公司指标的跨季度项目。
你的背景大致如下
- 拥有 2 年以上 engineering management 经验,在快速变化的环境中领导过高绩效团队。
- 具备扎实的技术深度和 IC 基础,能够指导架构、debug 复杂故障并做出合理的权衡。
- 有构建 distributed systems、execution engines、real-time platforms 或其他高规模系统的经验,其中正确性和可靠性至关重要。
- 有在模糊中交付跨季度项目的记录,能为团队和利益相关者创造清晰度。
- 深切关注 engineering craft 和 operational excellence,包括 testing strategy、observability 和 incident learning。
- 沟通清晰,能与 Product、Research 和 Infrastructure 团队良好协作。
如果还有以下经验则更佳
- 有 agent frameworks、runtimes、orchestration logic 或 tool use systems 的经验。
- 有 evaluation、experimentation 或 model quality measurement systems 的经验。
- 有为 safety-critical 或高可靠性系统构建 guardrails 的经验。
薪酬
$280,000 - $430,000 + 提供 Equity
福利
我们为全职员工自豪地提供以下福利:
- 为您和您的家人提供 Medical、Dental 和 Vision 福利
- Life Insurance 和 Disability Benefits
- Retirement Plan(例如 401K、pension)
- 通过 Carrot 提供的 Fertility 和家庭建设福利
- 每月津贴支持您的 wellness、lifestyle 和 work-life balance
- 办公室每日午餐和小食,让您保持最佳状态
- Take what you need 休假政策(需符合当地要求;英国员工享有 25 天 statutory leave)
这些福利在 Decagon 政策中有更详细的描述,可能因地点而异,并可根据适用的薪酬和福利计划随时变更。
译文仅供辅助阅读,具体要求以原始招聘来源为准。