Entity Resolution & Search Engineer

NimbleFig; California; Hybrid; USD 175,000 - 240,000; Full time

Benefits offered by this job

Remote across the US

In-person in San Francisco

Real ownership

Small senior team

Job summary

NimbleFig is a data company that builds and maintains data platforms turning public information into clean, structured, real-time data for people and machines. You will join a small, senior team focused on correctness and search quality.

You will design, implement, and evaluate entity resolution and ranking systems, work with embeddings, and scale a knowledge-graph-like entity graph to support cross-domain data. Remote options nationwide with SF in-person collaboration are available.

Qualifications

• Experience with entity resolution, record linkage, dedup, or search (lexical or vector).
• Solid information-retrieval or applied-ML fundamentals.
• Rigorous about evaluation, not just shipping a model.
• Comfortable in Python and working with large datasets.
• Built or tuned a production search system (Elasticsearch, a vector DB, or similar).
• Experience with embeddings, ranking, or learning-to-rank.
• Familiarity with knowledge graphs or graph data.

Responsibilities

• Build and improve entity resolution and record linkage across our platforms
• Design and tune search relevance across large, constantly changing corpora
• Own evaluation: define precision and recall, measure honestly, and improve deliberately
• Grow and maintain the entity graph that connects data across domains
• Turn fuzzy, ambiguous matching problems into systems that hold up in production

Skills

Entity resolution

Information retrieval

Evaluation metrics

Python

Large datasets

Production search system

Embeddings

Knowledge graphs

Tools

Elasticsearch

Vector DB

Python

Job description

Public information is written a thousand different ways, and the same entity shows up under a hundred names. Your job is to decide when two things are the same thing, resolve them into one clean record, and make the result fast and accurate to search. This work ties our platforms together across news, places, government, and markets.

About NimbleFig

NimbleFig is a data company. We acquire and operate data platforms that turn the world's public information into clean, structured, real-time data for people and machines, across news, places, government, and markets. Most of it is written for human eyes, scattered across millions of sources, and out of date the moment it ships. Our job is to make each part of that record complete, current, and ready to query. We are a small, senior team, and the work is measured by one thing: whether the data is right, current, and easy to use.

What you'll do

• Build and improve entity resolution and record linkage across our platforms


• Design and tune search relevance across large, constantly changing corpora


• Own evaluation: define precision and recall, measure honestly, and improve deliberately


• Grow and maintain the entity graph that connects data across domains


• Turn fuzzy, ambiguous matching problems into systems that hold up in production

What we look for

• Experience with entity resolution, record linkage, dedup, or search (lexical or vector)


• Solid information-retrieval or applied-ML fundamentals


• Rigorous about evaluation, not just shipping a model


• Comfortable in Python and working with large datasets


• Built or tuned a production search system (Elasticsearch, a vector DB, or similar)


• Experience with embeddings, ranking, or learning-to-rank


• Familiarity with knowledge graphs or graph data

Compensation

Depending on experience, the expected pay range in California is $175K–$240K.

What we offer

• Competitive pay, in the range listed above


• Remote across the US, or in person in San Francisco


• Real ownership: you will ship work that customers depend on


• A small, senior team with high standards and little process