高级主任软件工程师-搜索质量
查看雇主原标题
Senior Staff Software Engineer- Search QualityDatabricks · Bengaluru, 印度
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-1408
使命
我们正在为每一位企业用户普及数据与 AI。我们的愿景是让任何人都能通过应用和 AI 智能体掌握其组织的数据。我们正在为两个世界构建检索骨干：面向 AI 智能体的高精度上下文层，以及面向人的直观搜索体验。目标是一致的：即时、准确、可执行的洞察。
岗位职责
• 作为搜索质量工程师，你正处于这一变革的核心。你不仅仅是在构建一个搜索引擎；你正在构建整个公司的上下文骨干。
• 你将负责两个不同但深度相连的“用户”的结果质量：
• AI 智能体：优化检索层，使 LLM 能够对它们未曾训练过的数据进行推理，确保它们拥有合成准确、高风险业务行动所需的“真实依据”。
• 人类用户：改善传统搜索体验，使员工能够通过直观、高召回率的界面找到资产和答案。
技术挑战
这不是一个已经解决的问题。你将应对“搜索”最进化的形态：
• 混合检索：在传统基于关键词的搜索（追求精确性）与语义向量搜索（追求意图）之间取得平衡。
• 双重优化：微调排序模型，使其同时满足人类可读性和 LLM 就绪的上下文。
• 高风险准确性：在智能体的世界里，糟糕的搜索质量会导致幻觉。你将构建护栏和相关性评分，确保我们的 AI 始终扎根于现实。
• 数据异构性：在结构化 SQL 表、非结构化文档和实时业务指标之间建立联系。
为什么这里是理想之地
• 你将拥有智能体革命的前排座位。如果你想解决数据发现中最困难的问题，并看到你的工作为数千人的决策提供动力，让我们聊聊。
任职要求
• IR 专家：你熟悉 Lucene/Elasticsearch、嵌入和排序算法。
• 质量与指标偏执狂：你理解“相关性”是主观的，并且热爱构建评估框架（人在回路和基于 LLM 的）来衡量它。你对相关性指标（nDCG、MRR、Precision@K）痴迷。
• 桥梁搭建者：你热衷于将传统信息检索（IR）智慧应用于检索增强生成（RAG）这一前沿领域。
关于 Databricks
Databricks 是一家数据与 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——依赖 Databricks 数据 + AI 平台来构建和扩展数据与 AI 应用、分析和智能体。Databricks 总部位于旧金山，在全球拥有 30 多个办事处，提供统一平台，包括 Genie、Lakebase、Agent Bricks、Lakeflow、Lakehouse 和 Unity Catalog。如需了解更多，请在 LinkedIn、X、YouTube 和 Instagram 上关注 Databricks。
福利待遇
在 Databricks，我们努力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，我们致力于培育一种多元且包容的文化，让每个人都能脱颖而出。我们非常谨慎地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、社会经济地位、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职位申请美国政府许可证，且雇主可能仅基于此理由拒绝继续推进某位申请人。
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-1408
The Mission
We are democratizing Data and AI for every enterprise user. Our vision is a world where anyone can master their organization’s data through Apps and AI Agents. We are building the retrieval backbone for two worlds: the high-precision context layer for AI agents and the intuitive search experience for people goal is the same: instant, accurate, and actionable insight.
岗位职责
• As a Search Quality Engineer, you sit at the heart of this transformation. You aren't just building a search engine; you are building the contextual backbone of the entire company.
• You will own the quality of results for two distinct but deeply connected "users":
• The AI Agent: Optimizing the retrieval layer that allows LLMs to reason over data they weren’t trained on, ensuring they have the "ground truth" needed to synthesize accurate, high-stakes business actions.
• The Human User: Improving the traditional search experience so employees can find assets and answers through intuitive, high-recall interfaces.
The Technical Challenge
This isn't a solved problem. You will be tackling "Search" in its most evolved form:
• Hybrid Retrieval: Balancing traditional keyword-based search (for exactness) with semantic vector search (for intent).
• Dual-Optimization: Fine-tuning ranking models that satisfy both human readability and LLM-ready context.
• High-Stakes Accuracy: In a world of Agents, poor search quality leads to hallucinations. You will build the guardrails and relevance scoring that ensure our AI stays grounded in reality.
• Data Heterogeneity: Connecting the dots across structured SQL tables, unstructured docs, and real-time business metrics.
Why This is the Place to Be
• You will have a front-row seat to the Agentic revolution. If you want to solve the hardest problems in data discovery and see your work power the decision-making of thousands of people, let’s talk.
任职要求
• The IR Specialist: You know your way around Lucene/Elasticsearch, embeddings, and ranking algorithms.
• The Quality and Metrics Obsessive: You understand that "relevance" is subjective and love building evaluation frameworks (human-in-the-loop and LLM-based) to measure it. You are obsessed with relevance metrics (nDCG, MRR, Precision@K).
• The Bridge Builder: You’re excited to apply traditional Information Retrieval (IR) wisdom to the cutting-edge world of Retrieval-Augmented Generation (RAG).
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 .
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.