人工智能后端工程师（代理系统）
AI Backend Engineer (Agent Systems)
关于公司
我们的客户是一家由东南亚领先科技公司支持的隐秘人工智能初创公司，目前正在组建其全球创始团队。
该公司正在开发一个以人工智能为核心的通信平台，旨在通过将人工智能直接整合到对话中，简化日常任务。用户无需在多个应用程序之间切换，即可在一个智能助手内完成计划、组织、比较、研究和完成任务。
面向仍依赖传统生产力工具的数十亿用户市场，该平台专注于提供可靠的AI工作流程、持久上下文、多步骤推理和无缝任务执行。其使命是打造一款显著提升生产力的AI助手，使日常工作的操作更简单、更直观。
关于职位
我们的客户正在寻找一名AI后端工程师，负责构建和运营支撑其产品中AI驱动体验的后端基础设施。该职位重点在于负责位于AI模型与终端用户之间的推理和编排层，确保每一次交互都快速、可靠、可扩展且成本高效。
与工程和AI团队紧密合作，该职位将在设计生产级后端服务、优化系统性能以及跨移动和桌面平台交付强大的AI功能方面发挥关键作用。
主要职责
- 构建、维护并运营支撑生产环境中AI功能的后端系统。
- 设计并实现围绕AI模型的推理流水线、编排层和服务架构。
- 开发可无缝集成前端应用和机器学习系统的可扩展、高性能API。
- 通过改进推理延迟、吞吐量、缓存、批处理和流处理能力来优化系统性能。
- 负责生产运维，包括监控、日志记录、警报和事件响应。
- 排查并解决分布式系统中的问题，以确保服务的可靠性与稳定性。
- 根据运营洞察和实际使用情况持续改进后端架构和生产系统。
- 与跨职能团队协作，交付可靠、可扩展且高质量的AI解决方案。
要求
- 在生产环境中具有扎实的后端工程经验。
- 具有构建和运营高吞吐、低延迟后端服务的实际经验。
查看英文原文
About the Company
Our client is a stealth AI startup backed by one of Southeast Asia's leading technology companies and is currently building its global founding team.
The company is developing an AI-native communication platform designed to simplify everyday tasks by integrating AI directly into conversations. Instead of switching between multiple applications, users can plan, organize, compare, research, and complete tasks within a single intelligent assistant.
Serving a market of billions of users still relying on traditional productivity tools, the platform focuses on delivering reliable AI workflows, persistent context, multi-step reasoning, and seamless task execution. The mission is to create an AI assistant that significantly improves productivity while making everyday work simpler and more intuitive.
About the Role
Our client is seeking a AI Backend Engineer to build and operate the backend infrastructure that powers AI-driven experiences across its products. The role focuses on owning the inference and orchestration layer that sits between AI models and end users, ensuring every interaction is fast, reliable, scalable, and cost-efficient.
Working closely with engineering and AI teams, this position will play a key role in designing production-grade backend services, optimizing system performance, and delivering robust AI-powered features across mobile and desktop platforms.
Key Responsibilities
- Build, maintain, and operate backend systems that power AI-enabled features in production.
- Design and implement AI inference pipelines, orchestration layers, and service architectures around AI models.
- Develop scalable, high-performance APIs that integrate seamlessly with frontend applications and machine learning systems.
- Optimize system performance by improving inference latency, throughput, caching, batching, and streaming capabilities.
- Own production operations, including monitoring, logging, alerting, and incident response.
- Troubleshoot and resolve issues within distributed systems to ensure service reliability and stability.
- Continuously improve backend architecture and production systems based on operational insights and real-world usage.
- Collaborate with cross-functional teams to deliver reliable, scalable, and high-quality AI-powered solutions.
Requirements
- Strong backend engineering experience in production environments.
- Proven experience building and operating high-throughput, low-latency backend services.
- Experience designing scalable APIs and distributed systems.
- Familiarity with AI inference patterns, including Large Language Models (LLMs), embeddings, and multimodal AI systems.
- Strong debugging and troubleshooting skills within distributed production environments.
- Demonstrated ability to deliver production-ready solutions while iterating based on real-world system performance.
- Excellent analytical, problem-solving, and collaboration skills.
Technical Skills
Experience with the following technologies is preferred:
- Python
- Node.js
- PyTorch
- OpenAI, Anthropic, or open-source Large Language Models (LLMs)
- SQL and NoSQL databases
- Kubernetes
- Docker
Originally posted on Himalayas