Senior Entity Resolution Engineer - Remote, Equity & PTO

defcon; United States; Remote; USD 160,000 - 195,000; Full time

Benefits offered by this job

Medical coverage

Dental coverage

Vision coverage

Unlimited paid time off

Flexible scheduling

Parental leave (14 weeks)

Job summary

defcon is seeking a senior data linkage engineer to build production-grade entity-resolution systems for a government-focused data platform. You will design and implement the end-to-end matching lifecycle, including blocking, candidate generation, scoring, clustering, and thresholding, with provenance and explainable decisions.

The role is fully remote in the United States with occasional travel to headquarters or partner sites.

Qualifications

• At least five years shipping record-matching or entity-resolution systems.
• Strong Python and SQL skills working on large, messy real-world datasets.
• Ability to explain matching tradeoffs to nontechnical stakeholders.
• U.S. citizenship and an active U.S. Secret clearance required at start.
• Experience with probabilistic matching and explainable provenance.

Responsibilities

• Implement the matching lifecycle: blocking, candidate generation, pairwise scoring, clustering, and threshold recommendations.
• Use a shared matching engine for record linkage, deduplication, and known-entity checks.
• Track origins of graph nodes, edges, and assertions for auditability.
• Evaluate candidate retrieval and final matching against a fixed reference dataset with evidence.
• Make false-merge and false-split tradeoffs explicit and explainable to nontechnical stakeholders.
• Document the matching logic as a practical engineering reference.

Skills

Python

SQL

Explain tradeoffs

Large datasets

Provenance & auditability

Tools

PostgreSQL

pgvector

record linkage tools (Splink/Dedupe)

AQL/SQL tooling

Job description

defcon is seeking a senior data linkage engineer to build production-grade entity-resolution systems for a government-focused data platform. You will design and implement the end-to-end matching lifecycle, including blocking, candidate generation, scoring, clustering, and thresholding, with provenance and explainable decisions.

The role is fully remote in the United States with occasional travel to headquarters or partner sites.