Terms of ServicePrivacy Policy

Knowledge Graph Engineer

Full-Time · Mid-SeniorWashington, DC / Remote (US)

Mission

You'll design, build, and continuously enrich the knowledge graph that powers our entire intelligence platform - the strategic foundation that connects every patent to every case, every examiner to their search methodology, every judge to their claim construction patterns.Build the memory that makes litigation intelligence possible.

Ready to Apply?

Remote-friendly team based in the Washington, DC metro area
Competitive salary, equity, and performance bonus
Comprehensive health coverage and flexible time off
Backed by elite investors and trusted by AmLaw 100 firms
Apply for this Role

Ex Parte is an equal opportunity employer.

What You'll Build

Entity Resolution at Scale

  • Unify patents, cases, parties, counsel, judges, and examiners across 10+ heterogeneous data sources
  • Disambiguate entities ("Apple Inc." vs. "Apple Corps") across millions of records using Databricks and PySpark
  • Build probabilistic matching systems that handle inconsistent naming (e.g., "John Smith" vs. "J. Smith" vs. "Smith, John")
  • Create audit trails that track entity merges and splits for legal defensibility

Relationship Extraction

  • Map prosecution history amendments to claim scope limitations
  • Connect examiner search queries to specific classification subgroups and databases
  • Link judge decisions to claim construction patterns
  • Trace patent families through continuations, divisionals, and reexaminations

Graph Reasoning & Optimization

  • Identify analogous prior art through classification lineage analysis
  • Detect patterns in examiner behavior (e.g., "Examiner X never searches NPL")
  • Support multi-hop queries (e.g., "Show me all patents by Company Y challenged by Company Z before Judge A")
  • Optimize Neo4j query strategies for sub-second response times on billion-node graphs

Requirements

  • 4+ years building production knowledge graphs or graph-heavy data systems
  • Deep expertise with graph databases (Neo4j preferred, Cosmos DB or TigerGraph also relevant) and Cypher query language
  • Mastery of Databricks & PySpark for large-scale data processing
  • Strong understanding of entity resolution, record linkage, and data deduplication at scale
  • Experience working with messy, unstructured data sources
Bonus
  • Experience with RDF, SKOS, or semantic web technologies
  • Background in NLP for relationship/entity extraction from text
  • Prior work with legal, scientific, or government datasets
  • Familiarity with graph neural networks (GNNs)

Compensation

  • Base salary: $150,000 - $210,000 (based on experience)
  • Stock Options
  • Performance bonus eligibility