高级实体解析工程师
Senior Entity Resolution Engineer
DEFCON AI 是一家洞察公司，利用人工智能、数学优化、数据分析和软件工程，对复杂系统进行弹性优化。
在当今不断变化的世界中，DEFCON AI 的技术能够将结果与运营目标对齐，提升决策质量，并使客户能够预见、评估并减轻中断的影响。
**职位描述**
该职位位于平台最关键的部分之一：确定来自数十个不同来源的记录是否代表同一个现实世界中的实体。图设计和匹配策略是在内部开发的，**你将作为工程师，将这些概念转化为可投入生产的功能。** 你将决定实现细节，但这是一个以构建为主的角色。
你将加入一个为政府真实任务需求构建技术的团队。该平台从各种来源获取和分析数据，应用 AI 辅助的工作流程来突出最重要的信息，并提供透明、可解释的建议，分析师可以信任这些建议。你创建的每一个匹配、合并和关系都将帮助将碎片化信息转化为洞察。
你将全程负责匹配构建生命周期：阻塞策略、候选生成、成对评分、聚类、阈值策略，以及重复数据删除和已知实体检查，这些都使用相同的引擎。你还将构建溯源框架，使图中的每个节点、边和断言都能追溯到其来源，从而使匹配决策可审计且可解释。
这是一个完全远程的职位，根据需要偶尔需要前往 DEFCON AI 总部、客户现场和合作伙伴设施。
**主要职责**
- 实现和优化实体级别的记录匹配：阻塞、候选生成、成对评分、聚类和阈值策略
- 使用同一匹配引擎进行记录链接、去重和已知实体检查
- 建立溯源机制，使每个节点和边都能追溯到其来源
- 负责匹配决策中的误合并与误拆分权衡，并使其可解释
- 负责按照内部设计执行匹配方法：固定参考数据集、候选检索和最终匹配分别评估，以及带有证据的阈值建议供审查
- 记录匹配逻辑
查看英文原文
ABOUT DEFCON AI
RESILIENCE IN THE FACE OF DISRUPTION. DEFCON AI is an insights company that leverages artificial intelligence, mathematical optimization, data analytics, and software engineering for resilient optimization of complex systems.
In today’s dynamically changing world, DEFCON AI’s technology aligns outcomes with operational goals, better decision making, and empowers customers to anticipate assess, and mitigate the impacts of disruptions.
**About the Role**
This role sits in one of the most critical parts of the platform: determining when records from dozens of disparate sources represent the same real-world entity. Graph design and matching strategy are developed in-house, and **you’ll be the engineer who turns those concepts into production-ready capability.** You’ll shape implementation details, but this is first and foremost a builder role.
You’ll join a team building technology that supports real-world government mission needs. The platform ingests and analyzes data from a wide range of sources, applies AI-assisted workflows to surface what matters most, and provides transparent, explainable recommendations that analysts can trust. Every match, merge, and relationship you create helps turn fragmented information into insight.
You’ll own the matching build lifecycle end to end: blocking strategies, candidate generation, pairwise scoring, clustering, threshold policy, and the deduplication and known-entity checks that reuse the same engine. You’ll also build the provenance framework that lets every node, edge, and assertion in the graph be traced to the source that asserted it, so matching decisions are auditable and explainable.
This is a fully remote role with occasional travel to DEFCON AI headquarters, customer sites, and partner facilities as needed.
**Key Responsibilities**
- Implement and refine entity-level record matching: blocking, candidate generation, pairwise scoring, clustering, and threshold policy
- Reuse one matching engine for record linkage, deduplication, and known-entity checks
- Establish provenance so every node and edge traces back to the source that asserted it
- Own the false-merge versus false-split tradeoff in matching decisions and make it explainable
- Own technical execution of the matching approach against the in-house design: the fixed reference dataset, candidate retrieval and final matching evaluated separately, and threshold recommendations with evidence for review
- Document matching logic in enough detail to serve as an implementation reference for other engineers
**Required Qualifications**
- 5+ years of experience, including shipping production record matching or entity resolution
- Ability to explain the matching tradeoffs you made, including how you handled false merges versus false splits
- Strong Python and SQL, with demonstrated experience on large, messy, real-world data
- Ability to explain a matching decision to a stakeholder who must defend it without understanding its internals
- US Citizenship Required
- Active US Secret clearance required to start
**Preferred Qualifications**
- Direct experience applying probabilistic matching to inconsistent identity data such as names, dates, addresses, and identifiers, and familiarity with the failure modes of each
- Familiarity with probabilistic record-linkage frameworks and tooling such as Fellegi-Sunter models, Splink, Dedupe, Zingg, or an in-house equivalent
- Record linkage, master data management, or identity management experience
- Graph data modeling and graph algorithms applied in production
- PostgreSQL and pgvector or comparable
- Active Top Secret clearance
**What Success Looks Like**
- Matching decisions that can be explained and defended to a non-technical reviewer
- A data model and matching pipeline the rest of the team can build on without redesigning it
- Provenance intact end-to-end, so every match traces to its source
**What We Offer**
- A fully remote, results-based environment
- Competitive salary, bonus, and equity package
- 100% employer paid, comprehensive health insurance including medical, dental, and vision for you and your family
- Unlimited PTO, with your manager’s approval
- Flexible work environment where you manage your work day
- 14 weeks of fully-paid parental leave
**Salary Range:** $160,000—$195,000. This represents the typical salary range for this position based on experience, skills, and other factors.
We’re an Equal Opportunity Employer: You’ll receive consideration for employment without regard to race, sex, color, religion, sexual orientation, gender identity, national origin, protected veteran status, or on the basis of disability.
* * *
**_Applicant Data Disclosure_**
_By submitting an application, you acknowledge that Defcon AI uses third-party service providers to facilitate its recruitment and hiring processes. These providers include applicant tracking systems, candidate verification platforms, and fraud detection tools (collectively, "Hiring Platforms"). Your application materials, including your résumé, cover letter, work samples, responses to application questions, and any other information you submit, may be transmitted to and processed by these Hiring Platforms for the following purposes:_
- _Managing and administering your application throughout the hiring process;_
- _Verifying the accuracy and authenticity of application materials, including by cross-referencing information you provide against publicly available sources and proprietary databases;_
- _Identifying indicators of potentially fraudulent, fabricated, or materially misleading application content, including but not limited to discrepancies between submitted materials and publicly available professional profiles, geographic anomalies, and fabricated work histories._
_Applications that are flagged through this process as containing indicators of fraud or material misrepresentation may be declined from further consideration. If you have questions about the status of your application or the evaluation process, please contact [recruiting@defconai.com](mailto:recruiting@defconai.com)._
_Defcon AI requires its Hiring Platform providers to process your information solely for the purposes described above and in accordance with applicable law. Your information will be retained only for as long as necessary to fulfill these purposes and any applicable legal obligations, after which it will be deleted in accordance with Defcon AI's data retention policies._
_For more information about how your data is used, please refer to our Privacy Policy and_ _[Applicant Privacy Notice](https://nam09.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.redcellpartners.com%2Fapplicant-privacy-policy%2F&data=05%7C02%7Ckat.creamer%40redcellpartners.com%7Cc0f94f3daed94dc7503108de8b61955e%7Cf861de501a2a42359dbf28afd57d1d97%7C0%7C0%7C639101448841578570%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=WoPiBMZqQyPPK5N4E1sCagkbMY2S8P3aSRSoy7T4los%3D&reserved=0)_ _._