高级资深应用AI工程师 - 上下文检索
查看雇主原标题
Senior Staff Applied AI Engineer - Context RetrievalDatabricks · Mountain View, California; San Francisco, California
职位信息来自雇主公开的招聘页面。申请前请务必在雇主官网核实详情。
为什么值得关注？
发现指数 42/100，仅依据与该职位一起存储的证据计算。
- 新的雇主官方职位
分数构成
- 时效性 （随职位发布时间变化）+18
- 雇主官方来源+15
- 稀有职位+1
- 公司来源健康度+8
该职位未包含：已披露薪资、远程职位、提及签证担保、提及搬迁、未出现在监控的职位板上。
这些理由来自雇主自己的职位描述与我们核实过的来源检查结果。除了已存储的信号之外，我们不做任何推测。
职位描述
机器翻译P-1549
在 Databricks，我们热衷于帮助数据团队解决世界上最棘手的问题——从让下一代交通工具成为现实，到加速医学突破的研发。我们通过构建和运行全球最佳的数据与 AI 基础设施平台来实现这一目标，让我们的客户能够利用深度数据洞察来改进其业务。
使命
Databricks 智能体的能力取决于其能够检索到的上下文。无论智能体是在回答关于上季度营收的问题、调试失败的作业、针对包含 10,000 张表的湖仓生成 SQL，还是总结 Wiki 页面，其质量都受限于它能找到什么——以及它对所找到内容的理解程度。
我们正在招聘一名 Senior Staff Applied AI Engineer，负责跨 SaaS 提供商为 Databricks 智能体构建上下文检索能力。这是一个从零到一的岗位，包含两项紧密关联的职责：
• 构建检索技术栈——涵盖查询理解、内容理解、排序、检索和评估——面向存储在多个系统中的企业 SaaS 数据。
• 构建位于该技术栈之上的搜索子智能体，负责推理需要什么上下文、如何检索上下文，以及是否正确的内容实际被返回——闭合智能体意图与为其提供服务的底层基座之间的环路。
如果你拥有深厚的信息检索智慧，交付过用于 RAG 和智能体工作负载的检索系统，并希望构建让每个 Databricks 智能体都显著更聪明的基座——以及构建于其上的智能体——那么这个岗位就是为你准备的。
岗位职责
• 从零构建完整的检索技术栈。负责端到端系统：查询理解、内容理解与索引、混合检索、排序和评估。做出将定义未来数年 Databricks 智能体如何访问上下文的架构决策。
• 跨异构数据进行检索——包括结构化和非结构化数据。对结构化资产（表、列、SQL 查询、仪表板、代码、notebook、作业）和非结构化内容（文档、wiki、工单、聊天、图像、视频、音频）进行索引和排序。每种模态都有其自身信号——设计能够利用这些信号而非将其抹平的检索方案。
• 连接客户实际使用的 SaaS 范围。为企业知识所在的系统构建连接器和检索适配器。对每个检索源分别处理其自身的新鲜度、权限和排序信号。
• 同时为两类消费者优化。检索必须同时服务于 LLM（有依据、token 高效、抗幻觉的上下文）和人类（直观、可解释的发现）。这些是不同的目标，需要不同的信号——两者都要负责。
• 攻克面向智能体的查询理解。智能体查询不像网页查询。构建针对多轮智能体工作流调优的查询重写、分解、意图分类和实体解析。
• 攻克大规模内容理解。构建从每种受支持资产类型中提取结构、实体、嵌入、摘要和元数据的流水线——并随着客户数据演进保持其新鲜度。
• 构建能够对检索进行推理的搜索子智能体。设计智能体层，由其决定需要什么上下文、查询哪些来源、如何分解和路由搜索，并且关键的是，判断检索到的内容是否真的足以回答问题。这些子智能体将规划多跳搜索，在结果较弱时发出后续查询，依据检索到的证据为论断提供依据，并将高置信度上下文（或失败信号）交回上游智能体。这是 IR 与智能体推理的交汇之处。
• 为检索和子智能体构建评估飞轮。搭建离线评估（nDCG、MRR、Recall@K、Precision@K）、LLM-as-judge 测试框架、人在回路标注和在线实验。将评估扩展到排序指标之外，以衡量子智能体的决策质量——它是否提出了正确的后续问题？它是否正确识别出检索失败？它是否将答案建立在正确的证据之上？无法衡量的质量就是无法交付的质量。
• 制定技术方向并发展团队。制定多年路线图，指导资深工程师，与研究、产品和平台负责人合作，并提升整个组织的技术标准。
任职要求
• 10 年以上软件工程经验，其中大量时间用于大规模构建生产级检索、搜索或 RAG 系统。
• 深厚的信息检索（IR）专业知识：词法检索（BM25、Lucene/Elasticsearch/OpenSearch）、稠密检索（嵌入、ANN 索引——FAISS、ScaNN、HNSW）、混合检索和学习排序。
• 具备现代 LLM 时代检索的实操经验：RAG 架构、查询重写、使用交叉编码器重排序、长上下文策略，以及减少幻觉的 grounding 技术。
• 具备在检索之上设计智能体系统的经验——搜索规划器、多跳/迭代检索、自我反思与充分性检查、决定获取什么并验证返回内容的工具使用型智能体。
• 对相关性评估有扎实掌握：nDCG、MRR、Precision@K、Recall@K；离线/在线实验；LLM-as-judge 框架；构建人工标注流水线。
• 具备跨结构化和非结构化数据工作的经验——你曾在同一系统中对表、代码和文档进行索引和排序，并对如何做好这件事有自己的见解。
• 具备从 0 到 1 构建的业绩记录：你曾从空仓库搭建检索系统，做出基础架构决策，并将其发展为客户依赖的产品。
• 展现出作为技术领导者运作的能力：跨团队制定方向，指导资深工程师，并与研究、产品和平台合作伙伴一起影响路线图。
加分项
• 具备在企业 SaaS 来源之上构建检索的经验（权限、新鲜度、多租户、ACL 感知索引）。
• 具备智能体系统、工具使用或面向 LLM 智能体的多轮检索背景。
• 对开源 IR/搜索项目的贡献，或在 SIGIR、KDD、WWW、EMNLP 或类似会议上的发表。
• 具备训练或微调嵌入模型、重排序器或查询理解模型的经验。
为什么选择这个岗位
• 基础性影响。检索是影响智能体质量的最大杠杆。你构建的技术栈将位于每个 Databricks 智能体以及我们平台上每个客户构建的智能体之下。
• 兼具规模化的绿地项目。你将获得罕见的组合：从一张白纸开始，同时立即接触大规模企业级规模、真实客户数据和世界级研究组织。
• 合适的团队。你将与 Lakehouse、Apache Spark™、Delta Lake、MLflow、MosaicML 和 DBRX 背后的工程师和研究人员并肩工作。
工作地点
该岗位位于我们加州 Mountain View 或加州 San Francisco 办公室。预计采用混合办公协作模式。
福利待遇
在 Databricks，我们致力于提供满足所有员工需求的全面福利和津贴。如需了解您所在地区所提供福利的具体详情，请点击此处。
我们对多元与包容的承诺
在 Databricks，我们致力于培育多元包容的文化，让每个人都能脱颖而出。我们非常重视确保我们的招聘实践具有包容性，并符合平等就业机会标准。在 Databricks 寻求就业机会的个人不会因年龄、肤色、残疾、族裔、家庭或婚姻状况、性别认同或表达、语言、国籍、身体和心理能力、政治派别、种族、宗教、性取向、社会经济状况、退伍军人身份及其他受保护特征而受到区别对待。
合规
如果履行工作职责需要访问受出口管制的技术或源代码，雇主可自行决定是否为此类岗位申请美国政府许可证，且雇主可能仅基于此原因拒绝继续推进某位申请人。
薪资
Databricks 致力于公平公正的薪酬实践。该岗位的薪酬范围列于下方，代表非佣金制岗位的预期薪资范围或佣金制岗位的目标收入。实际薪酬方案取决于每位候选人独有的若干因素，包括但不限于与工作相关的技能、经验深度、相关认证和培训，以及具体工作地点。基于上述因素，Databricks 预计将使用该范围的完整宽度。该岗位的总薪酬方案还可能包括年度绩效奖金、股权以及上述福利的资格。如需了解您所在地点属于哪个范围的更多信息，请访问我们的页面此处。
本地薪酬范围 $228,600 — $342,800 USD
关于 Databricks
Databricks 是数据与 AI 公司。全球超过 20,000 家组织——包括 adidas、AT&T、Bayer、Block、Mastercard、Rivian、Unilever，以及 70% 的《财富》500 强企业——依赖 Databricks Data + AI Platform 来构建和扩展数据与 AI 应用、分析和智能体。Databricks 总部位于 San Francisco，在全球拥有 30 多个办公室，提供统一平台，包括 Genie、Lakebase、Agent Bricks、Lakeflow、Lakehouse 和 Unity Catalog。如需了解更多信息，请在 LinkedIn、X、YouTube 和 Instagram 上关注 Databricks。
以上内容由机器翻译自动生成，可能存在错误；投递前请以雇主原文为准。
查看雇主原文
职位描述
P-1549
At Databricks, we are passionate about enabling data teams to solve the world's toughest problems — from making the next mode of transportation a reality to accelerating the development of medical breakthroughs. We do this by building and running the world's best data and AI infrastructure platform so our customers can use deep data insights to improve their business.
The Mission
Databricks agents are only as good as the context they can retrieve. Whether an agent is answering a question about last quarter's revenue, debugging a failing job, generating SQL against a 10,000-table lakehouse, or summarizing a Wiki page, its quality is bounded by what it can find — and how well it understands what it finds.
We are hiring a Senior Staff Applied AI Engineer to own context retrieval for Databricks agents across SaaS providers . This is a zero-to-one role with two deeply connected charters:
• Build the retrieval stack — query understanding, content understanding, ranking, retrieval, and evaluation — across the Enterprise SaaS data stored across multiple systems.
• Build the search subagents that sit on top of that stack and reason about what context is needed , how to retrieve it , and whether the right thing actually came back — closing the loop between an agent's intent and the substrate that serves it.
If you have deep Information Retrieval wisdom, have shipped retrieval systems for RAG and agentic workloads, and want to build the substrate — and the agents on top of it — that make every Databricks agent measurably smarter, this role is for you.
岗位职责
• Build the full retrieval stack from scratch. Own the end-to-end system: query understanding, content understanding and indexing, hybrid retrieval, ranking, and evaluation. Make the architectural calls that will define how Databricks agents access context for years to come.
• Retrieve across heterogeneous data — structured and unstructured. Index and rank across structured assets (tables, columns, SQL queries, dashboards, code, notebooks, jobs) and unstructured content (docs, wikis, tickets, chat, images, video, audio). Each modality has its own signals — design retrieval that exploits them rather than flattens them.
• Connect to the SaaS surface area customers actually use. Build connectors and retrieval adapters for the systems where enterprise knowledge lives. Treat each retrieval source with its own freshness, permissions, and ranking signals.
• Optimize for two consumers at once. Retrieval must serve both LLMs (grounded, token-efficient, hallucination-resistant context) and humans (intuitive, explainable discovery). These are different objectives and require different signals — own both.
• Crack query understanding for agents. Agent queries don't look like web queries. Build query rewriting, decomposition, intent classification, and entity resolution tuned for multi-turn agentic workflows.
• Crack content understanding at scale. Build the pipelines that extract structure, entities, embeddings, summaries, and metadata from every supported asset type — and keep them fresh as customer data evolves.
• Build search subagents that reason about retrieval. Design the agentic layer that decides what context is needed , which sources to query , how to decompose and route the search , and — critically — whether the retrieved content is actually sufficient to answer the question . These subagents will plan multi-hop searches, issue follow-up queries when results are weak, ground claims against retrieved evidence, and hand back high-confidence context (or signal failure) to upstream agents. This is where IR meets agentic reasoning.
• Build the evaluation flywheel for both retrieval and subagents. Stand up offline evals (nDCG, MRR, Recall@K, Precision@K), LLM-as-judge harnesses, human-in-the-loop labeling, and online experimentation. Extend evaluation beyond ranking metrics to measure subagent decision quality — did it ask the right follow-up? , did it correctly recognize when retrieval failed? , did it ground its answer in the right evidence? . Quality you can't measure is quality you can't ship.
• Set technical direction and grow the team. Set the multi-year roadmap, mentor senior engineers, partner with Research, Product, and Platform leaders, and raise the technical bar across the org.
任职要求
• 10+ years of software engineering experience, with significant time spent building production retrieval, search, or RAG systems at scale.
• Deep Information Retrieval (IR) expertise : lexical retrieval (BM25, Lucene/Elasticsearch/OpenSearch), dense retrieval (embeddings, ANN indexes — FAISS, ScaNN, HNSW), hybrid retrieval, and learning-to-rank.
• Hands-on experience with modern LLM-era retrieval : RAG architectures, query rewriting, re-ranking with cross-encoders, long-context strategies, and grounding techniques that reduce hallucination.
• Experience designing agentic systems on top of retrieval — search planners, multi-hop / iterative retrieval, self-reflection and sufficiency checks, tool-using agents that decide what to fetch and verify what came back.
• Strong grasp of relevance evaluation : nDCG, MRR, Precision@K, Recall@K; offline/online experimentation; LLM-as-judge frameworks; building human labeling pipelines.
• Experience working across structured and unstructured data — you've indexed and ranked over tables, code, and documents in the same system, and have opinions about how to do it well.
• Track record of building 0→1 : you've stood up a retrieval system from an empty repo, made the foundational architectural decisions, and grown it into something that customers depend on.
• Demonstrated ability to operate as a technical leader : setting direction across teams, mentoring senior engineers, and influencing roadmap with research, product, and platform partners.
Nice to Have
• Experience building retrieval over enterprise SaaS sources (permissions, freshness, multi-tenancy, ACL-aware indexing).
• Background in agentic systems, tool use, or multi-turn retrieval for LLM agents.
• Contributions to open-source IR/search projects, or publications at SIGIR, KDD, WWW, EMNLP, or similar venues.
• Experience training or fine-tuning embedding models, rerankers, or query understanding models.
Why This Role
• Foundational impact. Retrieval is the single biggest lever on agent quality. The stack you build will sit underneath every Databricks agent and every customer-built agent on our platform.
• Greenfield with scale. You get the rare combination of starting from a clean sheet and having immediate access to massive enterprise scale, real customer data, and a world-class research org.
• The right team. You'll work alongside engineers and researchers behind Lakehouse, Apache Spark™, Delta Lake, MLflow, MosaicML, and DBRX.
Location
This role is based in our Mountain View, CA or San Francisco, CA office. Hybrid in-office collaboration expected.
福利待遇
At Databricks, we strive to provide comprehensive benefits and perks that meet the needs of all of our employees. For specific details on the benefits offered in your region click here .
Our Commitment to Diversity and Inclusion
At Databricks, we are committed to fostering a diverse and inclusive culture where everyone can excel. We take great care to ensure that our hiring practices are inclusive and meet equal employment opportunity standards. Individuals looking for employment at Databricks are considered without regard to age, color, disability, ethnicity, family or marital status, gender identity or expression, language, national origin, physical and mental ability, political affiliation, race, religion, sexual orientation, socio-economic status, veteran status, and other protected characteristics.
Compliance
If access to export-controlled technology or source code is required for performance of job duties, it is within Employer's discretion whether to apply for a U.S. government license for such positions, and Employer may decline to proceed with an applicant on this basis alone.
薪资
Databricks is committed to fair and equitable compensation practices. The pay range(s) for this role is listed below and represents the expected salary range for non-commissionable roles or on-target earnings for commissionable roles. Actual compensation packages are based on several factors that are unique to each candidate, including but not limited to job-related skills, depth of experience, relevant certifications and training, and specific work location. Based on the factors above, Databricks anticipates utilizing the full width of the range. The total compensation package for this position may also include eligibility for annual performance bonus, equity, and the benefits listed above. For more information regarding which range your location is in visit our page here .
Local Pay Range $228,600 — $342,800 USD
About Databricks
Databricks is the Data and AI company. More than 20,000 organizations worldwide — including adidas, AT&T, Bayer, Block, Mastercard, Rivian, Unilever, and 70% of the Fortune 500 — rely on the Databricks Data + AI Platform to build and scale data and AI apps, analytics and agents. Headquartered in San Francisco with 30+ offices around the globe, Databricks offers a unified platform that includes Genie, Lakebase, Agent Bricks, Lakeflow, Lakehouse, and Unity Catalog. To learn more, follow Databricks on LinkedIn , X , YouTube , and Instagram .