高级应用人工智能工程师
Senior Applied AI Engineer
🚀 关于我们
我们是 StackBlitz 旗下的 Bolt.new！
我们带来了 WebContainers，这项开创性的技术让在浏览器中运行 Node.js 变得可能。这一突破开启了我们的旅程，自 2019 年以来，它支撑着每月超过 100 万开发者使用的极速在线 IDE。
但我们没有止步于此。
我们深入研究并构建了从想法到生产最快的方式，无需编写传统代码。这是一个下一代的、由 AI 驱动的应用程序构建器，可帮助你立即在浏览器中创建、编辑和部署全栈网页和移动应用。无需安装。无需配置。只需智能自动化和即时开发环境，让你以思维的速度前进。
我们是一个完全远程的团队，全球分布，深度协作，对构建软件开发的未来充满热情。
这是你加入一个拥有远大愿景的小团队的机会。如果你热爱快速交付、解决实际问题，并不断突破可能的边界，我们期待与你见面。
✨ 关于这个机会
作为 AI 团队的高级工程师，你将构建和改进驱动 Bolt.new 的核心编码 AI 代理。你将直接与产品、设计、工程和数据团队合作，解决关键的代理挑战：评估框架、上下文压缩、在大型代码库中保持上下文、编排直观的多步骤工作流，以及处理从简单的 UI 调整到复杂的架构决策等各种问题。
这不是 API 集成的工作。你将参与 AI 如何推理和生成全栈应用程序的构建，与经验丰富的工程师一起工作，在这个模式仍在创造的领域中。你的工作每天都会交付给数百万使用 Bolt.new 构建真实产品的用户。
🛠️ 你会如何贡献
- 为 Bolt.new 构建并发布最先进的编码代理（长期运行的工作流、上下文压缩、代理循环、模型路由）。
- 端到端负责代理功能：规划、工具使用、代码生成/编辑，以及在大型代码库和多轮会话中保持上下文。
- 集成和评估多个 LLM 供应商（OpenAI、Anthropic、Google）：基准质量/成本/延迟；为每个任务选择合适的模型；采用新模型功能。
- 设计安全、可靠的工具使用和工作流编排（例如 Vercel AI SDK、LangGraph）：结构化操作、防护措施和生产可观测性。
查看英文原文
🚀 About Us
We’re Bolt.new by StackBlitz!
We’re the team that brought you WebContainers, the first-of-its-kind technology that made it possible to run Node.js right inside your browser. That breakthrough kicked off our journey in 2019, and it’s what powers the blazing-fast online IDE used by over 1 million developers every month.
But we didn’t stop there.
We doubled down on everything we learned and built — the fastest way to go from idea to production without writing traditional code. It’s a next-gen, AI-powered app builder that helps you create, edit, and deploy full-stack web and mobile apps instantly, right in your browser. No installs. No setup. Just smart automation and instant dev environments that let you move at the speed of thought.
We’re a fully remote team, globally distributed, deeply collaborative, and seriously passionate about building the future of software development.
This is your chance to join a small team with a big vision. If you love shipping fast, solving real problems, and pushing the boundaries of what’s possible, we’d love to meet you.
✨ About This Opportunity
As a Senior Engineer on the AI team, you’ll build and improve the core coding AI agents that power Bolt.new. You’ll collaborate directly with product, design, engineering, and data to solve key agent challenges: evaluation harnesses, context compression, maintaining context across large codebases, orchestrating intuitive multi-step workflows, and tackling everything from simple UI tweaks to complex architectural decisions.
This isn't API integration work. You'll be contributing to how AI reasons about and generates full-stack applications, working alongside experienced engineers in a problem space where the patterns are still being invented. Your work ships to millions of users building real products with Bolt.new every day.
🛠️ How You'll Contribute
- Build and ship state-of-the-art coding agents for Bolt.new (long-running workflows, context compression, agent loops, model routing).
- Own agent capabilities end-to-end: planning, tool use, code generation/editing, and maintaining context across large codebases and multi-turn sessions.
- Integrate and evaluate multiple LLM providers (OpenAI, Anthropic, Google): benchmark quality/cost/latency; choose the right model for each task; and adopt new model features.
- Design safe, reliable tool-use and workflow orchestration (e.g., Vercel AI SDK, LangGraph): structured actions, guardrails, and production observability.
- Partner closely with product/design/engineering/data to deliver robust AI features; mentor and raise the bar for peers.
- Build and maintain evaluation harnesses and datasets; analyze failure modes and user feedback to continuously improve quality and reliability.
💡 Qualifications
- LLM Experience:Have shipped LLM agents to production environments used by thousands of users.
- Prompt Engineering: Deep understanding of prompt engineering best practices to guide LLM behavior. Able to craft, refine, and optimize prompts for different tasks and models.
- Software Engineering Skills: Solid software engineering fundamentals with experience in building production-ready systems.
- Autonomous Execution: Ability to deliver high-quality work with minimal oversight. Comfortable owning tasks end-to-end, managing complexity, and driving projects to completion within your functional area.
- Problem-Solving: Strong analytical and problem-solving skills with the ability to debug complex AI behaviors and bring clarity to ambiguous tasks.
- Data-Driven Mindset: Comfortable collecting, curating, and analyzing data to inform decisions. Able to build datasets, identify patterns in agent behavior, and translate findings into actionable improvements.
- Strong verbal and written English communication skills are required, as this role involves frequent collaboration with team members, stakeholders, and customers where English is the primary working language.
🎯 Bonus Points
- Machine Learning Background: Understanding of ML fundamentals and experience with model evaluation metrics.
- Open Source Contributions: Experience contributing to or maintaining open-source AI/ML projects.
- Research Background: Experience reading and implementing techniques from AI/ML research papers.
📌 A Few Notes
- You do not need a college degree to apply
- You do not need to be located in the U.S. — we’re remote-friendly
- You do not need to meet every qualification listed above
Originally posted on Himalayas