【深圳前端招聘】-猎头顾问深圳招聘信息-猎聘

成先生 3天前在线已认证

顾问(C) · 北京汇志博才管理咨询有限公司

聊一聊

职位介绍: Job Summary The Senior / Staff AI Engineer will lead the design and productionisation of enterprise-grade Generative AI and agentic systems. This role is responsible for turning business workflows into reliable AI capabilities by combining LLMs with retrieval, tools, memory, and orchestration patterns that can operate safely at scale. The role requires strong hands-on engineering depth across multi-agent architecture, Intelligent Document Processing (IDP), evaluation, observability, guardrails, and production operations, with a focus on building AI systems that are measurable, secure, maintainable, and ready for enterprise adoption across domains such as underwriting, claims, and customer service. Job Responsibilities Multi-Agent Architecture & Orchestration: Design and implement enterprise-grade AI agents and multi-agent systems for complex business workflows. Define architecture patterns for planning, routing, tool use, context handling, memory, and inter-agent coordination. Drive framework and platform choices across modern enterprise ecosystems such as Microsoft Agent Framework, Google Agent Development Kit (ADK), AWS-equivalent agent orchestration capabilities, and other production-ready agent platforms. RAG, Memory & Intelligent Document Processing (IDP): Build robust retrieval and document understanding pipelines that support high-value enterprise use cases. Design ingestion, parsing, chunking, indexing, retrieval, reranking, grounding, and memory strategies for structured and unstructured data. Apply Intelligent Document Processing to document-intensive workflows with clear goals around extraction quality, grounding accuracy, and reduction of hallucination risk. Production Engineering & Enterprise Integration: Build and operate AI capabilities as production services, APIs, and reusable components that integrate with enterprise microservices, backend systems, data platforms, and operational tools. Establish engineering patterns for reliability, scalability, fault tolerance, cost control, and maintainability, and work across teams to move solutions from prototype to production deployment. Evaluation, Safety & Observability: Define and implement evaluation and control mechanisms for agentic systems, including offline and online evaluation, traceability, tool-use validation, task success measurement, prompt and workflow regression testing, and production monitoring. Establish safety boundaries and guardrails such as input/output validation, approval checkpoints, access controls, policy enforcement, and auditability to support responsible and secure enterprise deployment. Job Requirements Education: Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Software Engineering, Data Science, or a related quantitative field. Experience: 5+ years of software engineering experience, including at least 2+ years of hands-on experience building and shipping LLM / GenAI applications in production. Proven track record in designing agentic systems, retrieval-augmented workflows, or AI-powered enterprise applications beyond proof-of-concept stage. Programming Skills: Strong proficiency in Python, including experience with asynchronous programming, clean coding standards, and version control (Git). Agent & GenAI Engineering: Strong hands-on experience with LLM application architecture, agent orchestration, multi-step workflow design, tool/function calling, retrieval, memory, and evaluation. Familiarity with enterprise-capable agent platforms or frameworks such as Microsoft Agent Framework, Google ADK, AWS-equivalent services, or comparable open-source solutions is expected. Enterprise Engineering: Solid understanding of microservice architectures, RESTful APIs, JSON-based integration, and enterprise system connectivity. Experience with production engineering concerns such as observability, testing, deployment, security, and service reliability is highly valued. Language Skills: Fluent in English, both written and spoken, and fully capable of using English as a professional working language. Preferred Skills Insurance / FinTech Background: Prior experience with financial services enterprise knowledge systems or Intelligent Document Processing scenarios involving policies, claims, risk, or other document-intensive workflows. AI Productivity Booster: Proficiency in using AI coding assistants such as Cursor or GitHub Copilot to accelerate development delivery. LLM Evaluation & Agent Quality: Familiarity with evaluation approaches for LLM and agent systems, including response quality, grounding, task success, tool-use reliability, and observability across multi-step workflows.

其他信息: 语言要求：粤语 + 英语; 行业要求：IT服务

猎聘温馨提示：

1. 如您发现平台内招聘方存在以下违规行为的，请立即举报

· 扣押您的身份证件或者其他证件；
· 要求您提供担保人、担保金或者以其他名义向您收取财物（如培训费、体检费、资料费、置装费、押金等）；
· 强迫您入股或者向您集资；
· 以招聘名义牟取不正当利益；
· 发布虚假招聘广告信息；
· 工作时长违反劳动法规定；
· 存在其他损害您的合法权益的行为。

2. 如您应聘的岗位属于涉外劳务合作/海外岗位的，请务必核实招聘方对外劳务合作资质取得情况，同时注意自身资金安全，防范招聘欺诈。

猎聘温馨提示：

猜你喜欢