Search & Relevance Engineer, Semantic / AI Search (Europe, Remote)

iDelsoft

Contract type

Ongoing

Work mode

Remote

Experience

Mid-level · 4+ years

Job description

A senior Search & Relevance Engineer role at a US-based B2B SaaS company, owning search quality across Elasticsearch filter search and AI natural-language search. The role is full-time and fully remote, focused on measuring relevance, finding failures, and shipping fixes.

At a glance

Employment: Full-time
Work mode: Remote

What you'll do

Own search quality across filter search (Elasticsearch) and AI search (natural language to filters)
Build relevance benchmarks, labeled query sets, offline evals and online metrics, tracking whether searches end in a saved result, a refined search, or an abandoned search
Tune Elasticsearch: mappings, analyzers, keyword and industry matching, scoring, synonyms, and handling of messy company names and domains
Build semantic and hybrid search: embed company and person profiles, run vector search alongside keyword search, and tune how the two are blended
Use embeddings to classify companies (industry, business type, B2B/B2C), group similar companies, and power 'companies like this one'
Improve AI search through prompts, schema, model choice and evals
Find where the data is missing or wrong, measure the impact, and recommend what to fix, enrich or buy
Benchmark data coverage, accuracy and freshness against external sources, and turn the results into a roadmap
Ship code across a TypeScript backend and Python analysis tooling, using AI to label data, analyze queries and run evals

What we're looking for

AI-native: builds with AI coding agents (Claude Code, Cursor, or similar) every day, runs agents for analysis and labeling, and can show how that makes them faster
Product mindset: starts from what the user was trying to do and why the search failed them, then picks the fix that changes their outcome and explains the trade-off to product and leadership
4+ years working on search, ranking or recommendations, with production Elasticsearch or OpenSearch experience (Solr or Vespa also count)
Production experience with embeddings: choosing and evaluating models, vector indexes (Elasticsearch dense_vector/kNN, pgvector, Qdrant), hybrid ranking such as reciprocal rank fusion, and managing index size, latency and re-embedding cost at hundreds of millions of rows
Has built relevance evaluations (judgment sets, precision@k, nDCG) and changed a product because of what they showed
Strong SQL and Python, comfortable shipping in a TypeScript/Node backend with AI agents
Has shipped LLM features: prompting, structured outputs, eval harnesses, and cost and latency trade-offs
Comfortable with messy entity data: company matching, deduplication, classification and industry taxonomies

Nice to have

Experience on a marketplace, e-commerce or B2B SaaS search team
Entity resolution or learning-to-rank experience
Has evaluated or integrated third-party data vendors

Benefits

A full-time, fully remote role
End-to-end ownership of search quality for a product used at large scale
An AI-native team where shipping with agents is the default
Direct work with product and leadership

Save