Search & Relevance Engineer, Semantic – AI Search

This is a fully remote position, open to applicants in Europe.

📋 Description

• Take charge of search quality for Elasticsearch filter search and AI search, transitioning from natural language to filters.

• Develop relevance benchmarks, labeled query sets, offline evaluations, and online metrics.

• Monitor the outcomes of searches, whether they result in saved results, refined searches, or abandoned searches.

• Optimize Elasticsearch mappings, analyzers, keyword and industry matching, scoring, synonyms, as well as handling messy company names and domains.

• Create semantic and hybrid search solutions by embedding company and person profiles and adjusting vector/keyword blending.

• Utilize embeddings to classify companies, group similar entities, and enhance related-company features.

• Enhance AI search capabilities through prompts, schemas, model selection, and evaluations.

• Identify and rectify missing or incorrect data, assess impact, and propose solutions, enrichment, or purchases.

• Compare data coverage, accuracy, and freshness against external sources and translate findings into a strategic roadmap.

• Deploy code within a TypeScript backend and Python analysis tools.

• Leverage AI for data labeling, query analysis, and large-scale evaluations.

⛳️ Requirements

• Senior Search & Relevance Engineer role at a rapidly expanding, US-based B2B SaaS company.

• AI-savvy: actively builds with AI coding agents such as Claude Code, Cursor, or similar on a daily basis.

• Possess a product-oriented mindset that prioritizes user outcomes and addresses search failures.

• Over 4 years of experience in search, ranking, or recommendations.

• Proven production experience with Elasticsearch or OpenSearch; experience with Solr or Vespa is also applicable.

• Hands-on experience with embeddings, including model selection and evaluation.

• Familiarity with vector indexes like Elasticsearch dense_vector/kNN, pgvector, or Qdrant.

• Experience in hybrid ranking techniques, such as reciprocal rank fusion.

• Capability to manage index size, latency, and re-embedding costs for datasets exceeding hundreds of millions of rows.

• Expertise in constructing relevance evaluations using judgment sets, precision@k, and nDCG metrics.

• Strong skills in SQL and Python.

• Comfortable delivering in a TypeScript/Node backend environment with AI agents.

• Experience in deploying LLM features, including prompting, structured outputs, evaluation harnesses, and balancing cost/latency trade-offs.

• Proficient in managing messy entity data, company matching, deduplication, classification, and industry taxonomies.

• Background in marketplace, e-commerce, or B2B SaaS search teams.

• Knowledge of entity resolution or learning-to-rank methodologies.

• Experience in evaluating or integrating third-party data vendors.

🏝️ Benefits

• Full-time, completely remote position.

• Comprehensive ownership of search quality for a product utilized on a large scale.

• AI-focused team where utilizing agents for deployment is standard practice.

• Direct collaboration with product teams and leadership.