DirectJobHub
Jobs · Engineering · California

Senior Engineer, Entity Graphs

Firmable · San Francisco Bay Area · 1 mo ago
HybridEngineeringFull-time

Overview

Firmable is the market-leading B2B sales intelligence platform in Asia Pacific, backed by leading investors, with 2,000+ customers and growing in the US. We build one of the richest datasets about businesses anywhere, resolving millions of companies and hundreds of sources into a single record.

Responsibilities

  • Own the graph systems underneath everything Firmable knows about a business. Design a hybrid store spanning graph, warehouse, and search, with a schema that keeps extending as new entity types and relationships arrive.

  • Build agentic retrieval, where agents plan traversals and assemble context on demand, at a scale of 15M companies and 130M people.

  • Develop entity resolution methods to decide when two records refer to the same real business, across multiple sources that each key and spell things differently.

  • Implement new linkage methods where standard ones break at our scale, and calibrate thresholds for precision and recall per source and match type.

  • Design and implement retrieval surfaces for agents, including parameterised traversals, subgraph projections, and interfaces that return slices rather than the entire store.

  • Optimize cost and latency per query as a first-class metric, and ensure the system catches a 1% error rate before a customer does.

Requirements

  • 6+ years building production data or graph systems, including at least one you designed and operated at scale.

  • A fully AI-native development workflow: agentic coding, AI-driven test generation, and automated review pipelines.

  • Experience with property graph databases like Neo4j, Memgraph, and Cypher.

  • Knowledge of graph algorithms at billion-edge scale, such as PageRank, community detection, and link prediction.

  • Experience with hybrid store design, including graph, warehouse, and search components.

  • Expertise in retrieval for machine consumers, including graph RAG and agentic retrieval.

  • Skills in search-side candidate retrieval, such as OpenSearch or Elasticsearch.

  • Experience with large-scale record linkage, especially where standard techniques fail.

  • Understanding of distributed processing, including Spark or Snowpark, with partitioning, skew handling, and incremental processing.

  • Experience with pipeline orchestration tools like dbt, Airflow, or Dagster.

  • Knowledge of registry data in production, such as ASIC, ABR, NZBN, Companies House, or SEC EDGAR.

  • Experience with inferred ownership attribution, such as shared IP addresses and multi-tenant infrastructure.

Qualifications

  • Ph.D. in Computer Science, Data Science, or related field.

  • Strong programming skills in Python, Java, or C++.

  • Experience with vector search or learning to rank.

  • Excellent communication and collaboration skills.

Benefits

Flexible work schedule, competitive compensation, equity options, professional development opportunities, and a supportive company culture.

Pay

Competitive salary commensurate with experience.

Schedule

Full-time position with a flexible work schedule to accommodate the needs of the team and the individual.

Similar jobs