wuyang
96 lines
2.5 KiB
Markdown
96 lines
2.5 KiB
Markdown
# Job: 百度 - 2027AIDU 智能体算法工程师
|
|
|
|
---
|
|
type: job
|
|
company: 百度
|
|
role: 2027AIDU-智能体算法工程师
|
|
location: 北京市
|
|
source_url: https://talent.baidu.com/jobs/list?projectType=3&recruitType=GRADUATE
|
|
source_name: 百度校园招聘
|
|
source_quality: official
|
|
collected_at: 2026-07-08
|
|
posted_at: 2026-05-12
|
|
first_seen_at: 2026-07-08
|
|
last_checked_at: 2026-07-08
|
|
snapshot_type: new
|
|
job_code: J99969
|
|
previous_snapshot:
|
|
status: active
|
|
level: graduate
|
|
team: AIDU项目
|
|
business_area: search / conversation / office / data platform / entertainment
|
|
employment_type: campus
|
|
salary:
|
|
skills:
|
|
- agent
|
|
- planning
|
|
- tool-use
|
|
- memory
|
|
- multi-agent
|
|
- rag
|
|
- agent-evaluation
|
|
topics:
|
|
- agent-architecture
|
|
- evaluation
|
|
- memory
|
|
models:
|
|
-
|
|
related_papers:
|
|
- 2025-vijayvargiya-openagentsafety
|
|
- 2026-memory-agent-survey
|
|
related_experiments:
|
|
-
|
|
related_projects:
|
|
-
|
|
relevance: high
|
|
---
|
|
|
|
## Source Snapshot
|
|
|
|
- source: 百度官方招聘页
|
|
- collected_at: 2026-07-08
|
|
- availability: 页面可访问，岗位列表显示发布日期 2026-05-12。
|
|
|
|
## Change Snapshot
|
|
|
|
- first_seen_at: 2026-07-08
|
|
- last_checked_at: 2026-07-08
|
|
- snapshot_type: new
|
|
- previous_snapshot:
|
|
- changed_fields:
|
|
|
|
## Raw JD Summary
|
|
|
|
百度 AIDU 的智能体算法岗位要求负责 AI Agent 设计和研发，覆盖感知、决策、执行闭环、多智能体协作、长期记忆、推理、规划、工具调用、反思、代码生成、RAG 融合和 Agent 评测体系建设。
|
|
|
|
## Responsibilities
|
|
|
|
- 设计和研发 AI Agent 的核心机制。
|
|
- 推动 Agent 在搜索、对话、办公、数据平台、网盘文库、生活娱乐等产品场景落地。
|
|
- 建设评测体系，优化成功率、延迟、成本和用户体验。
|
|
|
|
## Requirements
|
|
|
|
- 熟悉 ReAct、AutoGPT、CoT 等范式。
|
|
- 熟悉 LangChain、AutoGen、CrewAI 等 Agent 框架。
|
|
- 理解 RAG 与 Agent 融合架构。
|
|
|
|
## Extracted Signals
|
|
|
|
- hard requirements: planning、tool use、memory、multi-agent、RAG、eval。
|
|
- preferred skills: Agent 框架实践、产品场景落地。
|
|
- hidden signals: 百度把 Agent 从单点算法能力看成端到端系统能力。
|
|
- business direction: 搜索、对话、办公、数据平台和泛生活娱乐场景。
|
|
|
|
## Knowledge Links
|
|
|
|
- concepts: Agent loop, tool use, memory, evaluation
|
|
- papers: OpenAgentSafety, memory survey
|
|
- experiments: eval harness, memory benchmark
|
|
- projects:
|
|
|
|
## Gaps for Us
|
|
|
|
- 需要补充主流 Agent 框架的横向比较。
|
|
- 需要建立 Agent 评测指标和任务集。
|