美团【北斗】Agent构建算法研究员
校招全职核心本地商业-业务研发平台地点:北京状态:招聘
任职要求
【任职资格】 必备条件: 1.2027届计算机、人工智能、数学、统计、电子信息、自动化等相关专业,本科及以上学历,博士/硕士优先。 2.熟悉 LLM 及 Agent 基本机制与技术原理,包括 LLM API、KV Cache、Agent Loop、Tool Use、Reasoning、Planning、Skills、MCP、Memory、Subagent、Multi-Agent 等;对 Prompt Engineering、Context Engineering、Harness Engineering 等课题有较深入了解。 3.熟练使用 AI Agent 工具进行软件开发,在软件开发领域具有极强的学…
登录查看完整任职要求
微信扫码,1秒登录
工作职责
【愿景】 建成全球持续领先、客户长期信赖的履约技术平台,打造市场首选、社会认可、服务10亿用户的配送品牌。 【你将参与】 方向一:Agent 技术体系研究与 Harness 建设 1.面向真实业务场景,设计并构建 Agent 技术体系,重点攻克任务规划与分解、工具调用与协同、自我反思与纠错、记忆与知识管理等核心能力。 2.负责 Harness Agent 的开发与评估框架的搭建与持续迭代,抽象可复用的模式与组件。 3.深入分析 Agent 的失败模式,建立系统化的错误诊断、归因与自动修复机制。 方向二:Agent for Work 能力研究与探索 1.面向工作场景,设计并实现具备自主研究、知识库管理、自主循环能力的 Agent 系统。 2.重点攻克自主信息检索与整合、基于记忆与知识管理的结构化知识库动态更新、计划-执行-反思闭环等关键技术,实现工作流的高效自主执行。 方向三:业务闭环与落地 1.与业务团队深度协作,将 Agent 能力落地到真实业务流程中,解决实际业务痛点,并转化为可量化的线上收益。 2.建立覆盖 Agent 行为、任务完成质量、工具调用准确率和业务效果的评测体系,驱动模型与系统的快速迭代。
包括英文材料
学历+
大模型+
https://www.youtube.com/watch?v=xZDB1naRUlk
You will build projects with LLMs that will enable you to create dynamic interfaces, interact with vast amounts of text data, and even empower LLMs with the capability to browse the internet for research papers.
https://www.youtube.com/watch?v=zjkBMFhNj_g
AI agent+
https://www.ibm.com/think/ai-agents
Your one-stop resource for gaining in-depth knowledge and hands-on applications of AI agents.
缓存+
https://hackernoon.com/the-system-design-cheat-sheet-cache
The cache is a layer that stores a subset of data, typically the most frequently accessed or essential information, in a location quicker to access than its primary storage location.
https://www.youtube.com/watch?v=bP4BeUjNkXc
Caching strategies, Distributed Caching, Eviction Policies, Write-Through Cache and Least Recently Used (LRU) cache are all important terms when it comes to designing an efficient system with a caching layer.
https://www.youtube.com/watch?v=dGAgxozNWFE
MCP+
https://www.youtube.com/watch?v=eur8dUO9mvE
Unlock the secrets of MCP! 🚀 Dive into the world of Model Context Protocol and learn how to seamlessly connect AI agents to databases, APIs, and more. Roy Derks breaks down its components, from hosts to servers, and showcases real-world applications. Gain the knowledge to revolutionize your AI projects!
https://www.youtube.com/watch?v=L94WBLL0KjY
Let's talk about MCP or the Model Context Protocol.
Prompt+
https://cloud.google.com/vertex-ai/generative-ai/docs/learn/prompts/introduction-prompt-design
A prompt is a natural language request submitted to a language model to receive a response back.
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/prompt-engineering
These techniques aren't recommended for reasoning models like gpt-5 and o-series models.
https://www.youtube.com/watch?v=LWiMwhDZ9as
Learn and master the fundamentals of Prompt Engineering and LLMs with this 5-HOUR Prompt Engineering Crash Course!
质量保证+
https://roadmap.sh/qa
Steps to follow in order to become a modern QA Engineer
https://www.youtube.com/watch?v=AKLuQaPWcdg
Learn Testing And Quality Assurance Complete Course
还有更多 •••