后端工程师，AI（代理系统）
Backend Engineer, AI (Agent Systems)
关于 ActAI
目前有超过 50 亿用户在使用基础应用，如电子邮件、笔记、任务、日历，他们并不具备 AI 原生特性。我们的使命是为全球任何不习惯复杂提示的用户打造主动式应用。我们旨在通过最少甚至无需提示的方式，将智能带入对话、跑腿、组织和工作流中。
我们的产品专注于实现长期运行工作流的高可靠性、持久上下文和现实任务完成。我们相信产品将大大减少幻觉现象。
我们的目标是整理每个人的生活，让我们都能把时间花在有价值和有意义的事情上。
职位
作为后端工程师，AI，你负责支撑产品中每一次 AI 交互的推理和编排层。你的工作位于模型和用户之间，延迟、正确性、可靠性和成本直接影响真实用户体验。
你将构建和运营生产系统，将模型能力转化为跨移动端和桌面客户端使用的快速、稳定、可观察的 API。
重点
- 构建和运营支持生产环境 AI 功能的后端系统。
- 设计围绕模型的推理流水线、编排层和服务边界。
- 负责生产环境问题：监控、日志、警报和事件响应。
- 优化推理、缓存、批处理和流处理中的延迟和吞吐量。
理想经验
- 在生产环境中具备扎实的后端工程基础。
- 有运行高吞吐、低延迟服务的经验。
- 熟悉 AI 推理模式（LLMs、嵌入、多模态）。
- 能够在负载下调试分布式系统。
- 倾向于发布产品，并从生产行为中学习。
成果
- 后端系统在大规模下可靠运行，以低延迟和高吞吐量处理生产 AI 流量。
- APIs 稳定、清晰，支持与前端和 ML 系统的无缝集成。
- 生产事件能够被快速检测、诊断和解决，最小化用户影响。
- 基于真实使用情况的迭代改进持续提升系统性能和可靠性。
技术栈
- Python
- NodeJs
- Pytorch
- OpenAI / Anthropic / 开源 LLMs
- SQL & noSQL
- Kubernetes
- Docker
我们如何协作
当今世界上最好的产品是由小型、世界级团队打造的。我们是一个高人才密度且亲力亲为的团队。我们集体做出决策，快速推进，平衡速度与质量。
查看英文原文
About ActAI
There are over 5 billion users using basic applications today such email, notes, tasks, calendar and they're not AI-native. Our mission is to build proactive applications for anyone in the world, who are not used to complex prompting. We aim to bring intelligence to conversations, errands, organising and workflows, with minimal to no prompting.
Our product focuses on achieving high reliability for long-running workflows, persistent context, and real-world task completion. We believe products will greatly reduce hallucinations.
Our objective is to organise anyone's life, allowing us all to spend time on valuable and meaningful things.
Role
As a Backend Engineer, AI, you own the inference and orchestration layer that powers every AI interaction in the product. Your work sits between models and users, where latency, correctness, reliability, and cost directly impact real-world experience.
You will build and operate production systems that turn model capability into fast, stable, observable APIs used across mobile and desktop clients.
Focus
- Build and operate backend systems that serve AI-powered features in production.
- Design inference pipelines, orchestration layers, and service boundaries around models.
- Own production concerns: monitoring, logging, alerting, and incident response.
- Optimize latency and throughput across inference, caching, batching, and streaming.
Ideal Experiences
- Strong backend engineering fundamentals in production environments.
- Experience running high-throughput, low-latency services.
- Familiarity with AI inference patterns (LLMs, embeddings, multimodal).
- Comfortable debugging distributed systems under load.
- Bias toward shipping and learning from production behavior.
Outcomes
- Backend systems run reliably at scale, handling production AI traffic with low latency and high throughput.
- APIs are stable, clear, and support seamless integration with frontend and ML systems.
- Production incidents are quickly detected, diagnosed, and resolved, minimizing user impact.
- Iterative improvements based on real usage continuously increase system performance and reliability.
Tech Stack
- Python
- NodeJs
- Pytorch
- OpenAI / Anthropic / open-source LLMs
- SQl & noSQL
- Kubernetes
- Docker
How We Work
The best products today in the world were built by small, world class teams. We are a high talent density and hands-on team. We make decisions collectively, move at rapid speed, striking a balance between shipping high quality work and learning. Joining our team requires the ability to bring structure, exercise judgment, and execute independently. Our goal is to put in hands of our users a truly magical product
Interview process
If there appears to be a fit, we'll reach to schedule 3, but no more than 4 interviews.
Applications are evaluated by our technical team members. Interviews will be conducted via virtual meetings and/or onsite.
We value transparency and efficiency, so expect a prompt decision. If you've demonstrated the exceptional skills and mindset we're looking for, we'll extend an offer to join us. This isn't just a job offer; it's an invitation to be part of a team that's bringing AI to have practical benefits to billions globally.
Originally posted on Himalayas