AI工程师负责人 - 自主工程
Lead AI Engineer - Agentic Engineering
Blend 是一家领先的 AI 服务提供商，致力于通过数据科学、AI、技术与人才的合力，为客户创造有意义的影响。我们的使命是激发大胆的愿景，通过无缝结合人类专业知识与人工智能，解决重大的挑战。公司通过汇聚世界级的人才和数据驱动的战略，为客户解锁价值并推动创新。我们相信，人类与 AI 的力量可以对你的世界产生深远影响，为我们的员工和客户创造更有意义的工作和项目。更多信息，请访问 www.blend360.com。
我们正在寻找一名 首席 AI 工程师，帮助塑造和构建 Blend360 的下一代 自主代理 AI 和 AI 驱动的工程系统。
这不是一个传统的 GenAI 或聊天机器人开发岗位。我们寻找一位经验丰富的软件/AI 工程师，能够理解如何构建 生产级自主代理系统，并且重要的是，如何将 自主代理工程 作为软件开发生命周期（SDLC）的一部分加以利用。
你将参与 AI 工程、软件架构、代理编排、LLM 应用、开发者生产力和 AI 辅助软件开发。你将帮助建立围绕 AI 代理、上下文工程、工具使用、评估、自主任务执行和 AI 增强开发流程的工程实践。
理想的候选人具备扎实的软件工程基础，并有实际构建和运营真实世界自主代理 AI 系统的经验。
你将负责
自主代理工程与 AI 增强的 SDLC
· 推动在软件开发生命周期中采用自主代理工程实践，利用 AI 代理增强和自动化工程流程。
· 在日常软件开发中使用如 Claude Code、Claude Code Skills、PI、Hermes Agent 和类似 AI 编码/工程代理的工具和方法。
· 构建涵盖需求分析、代码生成、代码理解、重构、测试、调试、文档编写、代码审查和部署的 AI 辅助工作流。
· 设计能够理解大型代码库、管理上下文、使用工具、执行多步骤工程任务并从失败中恢复的代理工作流。
· 建立关于上下文管理、上下文工程、工具调用、代理编排、安全机制、人机协作流程和自主任务执行的最佳实践。
· 设计一套
查看英文原文
Blend is a premier AI services provider, committed to co-creating meaningful impact for its clients through the power of data science, AI, technology, and people. With a mission to fuel bold visions, Blend tackles significant challenges by seamlessly aligning human expertise with artificial intelligence. The company is dedicated to unlocking value and fostering innovation for its clients by harnessing world-class people and data-driven strategy. We believe that the power of people and AI can have a meaningful impact on your world, creating more fulfilling work and projects for our people and clients. For more information, visit www.blend360.com.
We are looking for a Lead AI Engineer to help shape and build the next generation of Agentic AI and AI-powered engineering systems at Blend360.
This is not a traditional GenAI or chatbot development role. We are looking for an experienced software/AI engineer who understands how to build production-grade agentic systems and, importantly, how to leverage Agentic Engineering as part of the Software Development Lifecycle (SDLC).
You will work across AI engineering, software architecture, agent orchestration, LLM applications, developer productivity, and AI-assisted software development. You will help establish engineering practices around AI agents, context engineering, tool use, evaluations, autonomous task execution, and AI-augmented development workflows.
The ideal candidate combines strong software engineering fundamentals with hands-on experience building and operating real-world Agentic AI systems.
What You'll Do
Agentic Engineering & AI-Augmented SDLC
· Drive the adoption of Agentic Engineering practices across the software development lifecycle, using AI agents to augment and automate engineering workflows.
· Leverage tools and approaches such as Claude Code, Claude Code Skills, PI, Hermes Agent, and comparable AI coding/engineering agents as part of day-to-day software development.
· Build AI-assisted workflows covering requirements analysis, code generation, code understanding, refactoring, testing, debugging, documentation, code review, and deployment.
· Design agent workflows capable of understanding large codebases, managing context, using tools, executing multi-step engineering tasks, and recovering from failures.
· Establish best practices around context management, context engineering, tool calling, agent orchestration, guardrails, human-in-the-loop workflows, and autonomous task execution.
· Design and implement Evals to measure agent correctness, reliability, code quality, task completion, regression, and overall effectiveness.
· Continuously evaluate emerging agentic coding tools and techniques and identify opportunities to improve engineering productivity and software quality.
Production-Grade Agentic AI
· Architect and develop multi-agent and agentic systems capable of performing complex, multi-step tasks in production environments.
· Design agent architectures involving planning, reasoning, tool use, memory/context, execution, reflection, validation, and error recovery.
· Build agents that integrate with APIs, databases, enterprise systems, developer tools, and other external services.
· Develop reliable tool-use and MCP-based integrations where appropriate.
· Build production-grade LLM applications using frameworks such as LangGraph, LangChain, or equivalent orchestration frameworks.
· Implement RAG, semantic search, vector retrieval, structured outputs, and other LLM application patterns where required.
· Establish appropriate observability, evaluation, monitoring, security, and guardrails for agentic applications.
Software Engineering & Architecture
· Provide technical leadership across the design and development of AI-powered software products and platforms.
· Apply strong software engineering principles including system design, modular architecture, API design, scalability, reliability, testing, CI/CD, and maintainability.
· Build production-quality services and APIs using technologies such as Python, FastAPI, Docker, Kubernetes, and cloud platforms.
· Work closely with engineering, product, data, and client teams to translate complex business problems into scalable technical solutions.
· Conduct technical design reviews and provide mentorship to other AI/software engineers.
· Establish engineering standards and best practices for building AI and agentic applications.
Leadership & Innovation
· Act as a technical leader for Agentic AI initiatives and influence architecture and engineering decisions across teams.
· Mentor engineers on AI engineering, agentic architectures, software engineering practices, and AI-assisted development.
· Stay current with rapidly evolving AI coding agents, agent frameworks, LLM capabilities, evaluation methodologies, and engineering practices.
· Prototype emerging technologies and transition successful approaches into reliable production solutions.
· Collaborate with clients and internal stakeholders to identify opportunities where Agentic AI can deliver measurable business and engineering value.
Must Have
· 6+ years of software engineering / AI engineering experience, with strong hands-on development experience.
· Strong software engineering fundamentals with experience building production-grade applications and services.
· Demonstrable experience building production-grade Agentic AI systems, beyond simple chatbots or basic RAG applications.
· Strong understanding of Agentic Evaluation / Agent Evals, including designing evaluation frameworks for autonomous and multi-agent systems.
· Experience creating evaluation datasets, test scenarios, metrics, automated regression tests, and quality gates for agentic applications.
· Ability to evaluate agents beyond final-answer accuracy, including planning, tool use, reasoning trajectory, context handling, reliability, safety, latency, cost, and task completion.
· Strong hands-on experience with Python and modern backend/API development.
· Experience with LLMs, GenAI, agent orchestration, tool calling, and RAG.
· Experience with agent frameworks such as LangGraph, LangChain, CrewAI, AutoGen, Google ADK, or equivalent.
· Strong understanding of multi-agent architectures, planning, reasoning, context management, tool use, memory, and agent execution.
· Experience working with Evals / evaluation frameworks to measure and improve AI/agent performance.
· Experience with cloud, containers, CI/CD, APIs, databases, and production deployments.
· Strong understanding of software architecture, debugging, testing, scalability, and production engineering practices.
Agentic Engineering – Critical Requirement
The candidate should have practical exposure to using AI agents as engineering tools within the SDLC, not simply developing AI applications.
Experience with tools such as:
· Claude Code / Claude Code Skills
· PI
· Hermes Agent
· AI coding agents or comparable agentic development platforms
is highly valuable.
Candidates should understand how to use these tools for activities such as:
Context management → code generation → repository understanding → implementation → testing → debugging → code review → evaluation → iteration
Nice to Have
· Experience with MCP (Model Context Protocol) and building MCP servers/tools.
· Experience with Claude, GPT, Gemini, Llama, or other frontier models.
· Experience with AWS, Azure, or GCP.
· Experience with Kubernetes, Docker, CI/CD, and cloud-native architectures.
· Experience with LLM observability and tracing.
· Experience with tools such as Langfuse, Arize Phoenix, OpenTelemetry, or similar.
· Experience implementing automated agent evaluations, regression testing, and quality gates.
· Experience with distributed systems and scalable AI inference.
· Experience working in consulting/client-facing environments.
What Success Looks Like
In this role, you will:
· Build and scale production-grade Agentic AI systems, not just prototypes or chatbots.
· Help Blend360 adopt Agentic Engineering across the SDLC.
· Improve developer productivity through AI-assisted engineering workflows.
· Establish repeatable approaches for context engineering, agent orchestration, tool use, and Evals.
· Help teams safely adopt AI coding agents such as Claude Code, PI, Hermes Agent, and emerging equivalents.
· Raise the engineering quality, reliability, and scalability of AI solutions delivered to clients.
· Mentor engineers and become a technical authority in Agentic AI Engineering.