岗位能力对标
Decagon

Staff Software Engineer, Agent Platform

San Francisco · 全职 · 工程与基础设施

源站发布:2025-12-01资料抓取:2026-11-10查看原始招聘来源

需要对标的能力

Agent · 智能体设计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 Platform 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 As a Staff Software Engineer on the Agent Platform team, you will design and build the systems that govern how Decagon agents operate in real-world environments. You will own complex, distributed systems that sit at the heart of the agent runtime: execution frameworks, model orchestration logic, and experimentation platforms that ensure agents are fast, reliable, and continuously improving. Your work will directly impact how agents reason, take actions, and deliver outcomes across millions of interactions. This role operates in a fast-moving, ambiguous space with tight feedback loops. You’ll move fluidly between diagnosing production issues, designing new system abstractions, and running experiments to improve agent behavior. You’ll collaborate closely with Research, Infra, and Product teams to ship improvements safely and at scale.   In this role, you will - Design and evolve agent harnesses that power different product experiences - Build core runtime systems, including AOP execution and multi-model orchestration - Develop control-plane logic for routing, planning, and tool invocation with strong safety guarantees - Optimize agent systems for latency, reliability, and production correctness - Analyze real-world failures and use data to drive iterative improvements - Build and operate online experimentation (A/B testing) and contribute to offline evaluation frameworks - Improve observability, testing, and simulation systems to ensure safe, measurable progress - Contribute to voice and real-time systems (e.g., transcription pipelines, turn-taking, latency improvements) - Continuously adapt orchestration systems as model capabilities evolve   Your background looks something like this - Strong experience building distributed systems or backend platforms in production environments - Comfort working in ambiguous, fast-moving environments with rapid iteration cycles - Experience owning systems end-to-end, from design through production and iteration - Familiarity with experimentation, evaluation, or data-driven product improvement loops - A track record of improving system reliability, performance, and observability - Ability to debug complex systems and identify root causes of failures   Even better - You’ve built or worked on agent harnesses, orchestration layers, or execution frameworks - You think in terms of control planes, feedback loops, and system-level optimization, not just features - You’re excited about diagnosing failure modes and iterating toward measurable improvements - You care deeply about production quality—not just making systems work, but making them reliable, safe, and scalable - You’re motivated by pushing the frontier of how intelligent systems behave in the real world   Compensation $200K – $400K + Offers Equity   This range reflects the expected compensation for this role. Compensation within the range is determined based on experience, skills, and the scope of responsibilities, with flexibility for candidates who demonstrate exceptional impact.   In addition to base salary, we offer competitive equity. Final compensation may vary based on location within the United States. 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能够部署 AI agent,在语音、聊天、邮件、短信及所有其他渠道上实现个性化、深度令人满意的交互,包括 Avis Budget Group、Block 旗下的 Cash App 和 Square、Chime、Oura Health 和 Hunter Douglas。 我们正在构建一个未来,客户体验将从 support tickets 和 hold music 转变为更快的解决方案、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,他们与我们共享这一愿景,包括 a16z、Accel、Bain Capital Ventures、Coatue 和 Index Ventures 等。 我们是一家要求员工到办公室办公的公司,以追求卓越和速度为共同承诺。我们的价值观——Just Get It Done、Invent What Customers Want、Winner's Mindset 和 The Polymath Principle——塑造了我们的工作方式和团队成长方式。 关于团队 Agent Platform 团队构建支撑 Decagon agent 在生产环境中运行的 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、低延迟且令人愉悦的体验。 这项工作的核心是 agent harness:routing、execution logic、tool orchestration 以及 control-plane 系统,它们决定了 agent 在实时对话中的行为方式。该团队负责每次对话的完整执行生命周期——从选择 workflows 和 orchestrating 多个模型(例如 router/planner/supervisor 模式),到 coordinating tool calls、enforcing safety constraints,再到与用户通信。 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,团队会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 作为 Agent Platform 团队的 Staff Software Engineer,你将设计并构建 governing Decagon agent 在真实环境中如何运作的系统。 你将拥有位于 agent runtime 核心的复杂分布式系统:execution frameworks、model orchestration logic 以及 experimentation platforms,确保 agent 快速、可靠并持续改进。你的工作将直接影响 agent 如何进行 reasoning、采取行动以及在数百万次交互中交付成果。 这一角色在快速变化、充满不确定性的空间中运作,具有紧密的 feedback loops。你将灵活地在诊断生产问题、设计新系统抽象以及运行实验以改进 agent behavior 之间切换。你将与 Research、Infra 和 Product 团队紧密协作,安全地、规模化地 ship improvements。 在这一职位中,你将 - 设计并演进支撑不同产品体验的 agent harnesses - 构建核心 runtime 系统,包括 AOP execution 和 multi-model orchestration - 开发用于 routing、planning 和 tool invocation 的 control-plane logic,并提供强有力的 safety guarantees - 针对 latency、reliability 和 production correctness 优化 agent systems - 分析真实世界的 failures 并使用数据驱动迭代改进 - 构建并运营 online experimentation(A/B testing),并贡献于 offline evaluation frameworks - 改进 observability、testing 和 simulation systems,以确保安全、可衡量的进展 - 贡献于语音和 real-time systems(例如 transcription pipelines、turn-taking、latency improvements) - 随着 model capabilities 的演进持续调整 orchestration systems 你的背景大致如下 - 在生产环境中构建分布式系统或 backend platforms 的丰富经验 - 适应在不确定、快速变化的环境中工作,具有 rapid iteration cycles - 端到端拥有系统的经验,从设计到生产再到迭代 - 熟悉 experimentation、evaluation 或 data-driven product improvement loops - 提升系统可靠性、性能和 observability 的 track record - 调试复杂系统并识别 failures root causes 的能力 更佳条件 - 你曾构建或参与过 agent harnesses、orchestration layers 或 execution frameworks - 你从 control planes、feedback loops 和 system-level optimization 的角度思考,而不仅仅是 features - 你对诊断 failure modes 并迭代实现可衡量的改进充满热情 - 你 deeply care about production quality——不仅仅是让系统工作,而是让它们可靠、安全且可扩展 - 你被推动 intelligent systems 在真实世界中行为的 frontier 所激励 薪酬 $200K – $400K + 提供 Equity 这一范围反映了该职位的预期薪酬。范围内的薪酬根据经验、技能和职责范围确定,对于展现出 exceptional impact 的候选人具有灵活性。 除基本工资外,我们提供具有竞争力的 equity。最终薪酬可能因在美国境内的 location 而有所不同。 福利 我们为全职员工自豪地提供以下福利: - 为你及家人提供的 Medical、Dental 和 Vision benefits - 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 stipend 以支持你的 wellness、lifestyle 和 work-life balance - 办公室每日午餐和零食,让你保持最佳状态 - Take what you need 休假政策(受当地要求约束;英国员工享有 25 天 statutory leave) 这些福利在 Decagon 的政策中有更详细的描述,可能因 location 而异,并可根据适用的 compensation 和 benefits plans 随时更改。

译文仅供辅助阅读,具体要求以原始招聘来源为准。