Hiring nowInformation retrieval and grounding

Search Relevance Engineer

Also called Retrieval Engineer

A Search Relevance Engineer improves how well a system finds the right evidence for the queries that matter. Better retrieval means grounded answers, fewer unsupported claims and a product people trust.

What they do

They take a set of target query types and make retrieval work better for them. They read failing queries, work out why results miss, and choose a fix. That might be query handling, lexical scoring, dense embeddings, a hybrid blend or a reranker. They build and maintain a judged query set, so changes are tested rather than guessed. They look at recall and ranking quality by query segment, not one average. They check index content, chunking and source quality, because bad inputs cap results. They work with application engineers on how retrieved evidence reaches the generation step.

What a strong hire delivers

In the first months, a strong hire delivers a working search pipeline aimed at the query types that matter most. They also leave a judged query set the team trusts and reruns after every change. Outcomes include a clear baseline, measured gains in recall and ranking by segment, a list of known weak spots, and a shared way to decide whether a retrieval change ships.

How you can tell they are good

Ask them to walk through one retrieval improvement from start to finish. A strong candidate names the query segment, shows the baseline, explains what they changed and what got worse as a result. They should talk comfortably about judgement quality, disagreement between judges and sampling. Ask how they would test a reranker. Be wary of anyone who only quotes a single overall score.

Why it is hard to fill

The title varies widely. Retrieval Engineer, search engineer, relevance engineer and NLP engineer can all describe the same work or very different work. Many candidates have deep classic search experience but little with dense or hybrid methods. Others know embeddings but have never built a judged set or handled messy production queries. The people who do both are few, and they are usually already well placed.

Where to find them

Look first at search teams in e-commerce, marketplaces, enterprise search and media, where relevance tuning is daily work. Also look at NLP engineers who have moved into retrieval, information science graduates who ended up in applied roles, and application engineers who built retrieval-augmented products and got drawn into quality. Teams running question answering over internal documents are another good source.

Indicative pay

Not enough published evidence yet to give a fair range for this role, which is common for work this new. We benchmark it for you as part of a search.

Interview questions for a Search Relevance Engineer

  1. Tell me about a retrieval failure you diagnosed. How did you find the cause and what did you change?

    A strong answer names specific queries, a clear diagnosis such as vocabulary mismatch, chunking or ranking, and a fix with evidence it worked. Worry if the story is vague, or if the fix was simply a bigger model.

  2. How would you build a judged query set for a new product with no search history?

    Look for sampling across expected query types, clear judging guidelines, more than one judge, and a plan to add real queries later. Worry if they rely only on synthetic queries or never check judge agreement.

4 more questions, with what a strong answer covers, are in the Role Kit.

Job description you can post

We are building products that answer questions from large bodies of evidence, and retrieval quality decides whether those answers can be trusted. We are looking for a Search Relevance Engineer to improve how we find evidence for the query types our users care about most.

What you will do

  • Improve retrieval quality for defined query types and segments
  • Build and maintain a judged query set and the process to run it
  • Design, tune and compare lexical, dense and hybrid retrieval
  • Evaluate and tune rerankers against quality, latency and cost
  • Diagnose failing queries and agree fixes with product and engineering
  • Review index content, chunking and source quality
  • Report recall and ranking quality by segment

What you will bring

  • Shipped retrieval or search improvements that were measured
  • Built or used judged query sets and can explain their limits
  • Hands-on with search engines and vector indexes
  • Understanding of lexical, dense and hybrid methods and their trade-offs
  • Comfortable writing production-quality code and evaluation scripts
  • Clear written explanation of results to non-specialists

Nice to have

  • Experience with retrieval-augmented generation systems
  • Work on data provenance or source quality
  • Experience tuning rerankers

Free to use and adapt. If it saves you time, a link back to this page is appreciated.

Skills that matter

  • Information retrievalAdvancedRetrieve and rank relevant documents or entities
  • Retrieval-augmented generationAdvancedGround generated responses in retrieved evidence
  • Data quality and provenanceWorkingTrack dataset origin, validity and transformations
  • Model evaluationWorkingMeasure capability and failure modes credibly

Other roles in information retrieval and grounding

Hiring nowRetrieval-Augmented Generation EngineerA RAG engineer builds the service that finds the right evidence and makes generated answers stick to it. It matters because users trust answers only…Hiring nowEnterprise Search ArchitectAn Enterprise Search Architect designs search that finds the right content across an organisation while respecting who is allowed to see what. It…EmergingGrounding Evaluation SpecialistA Grounding Evaluation Specialist tests whether an AI system's claims actually follow from the evidence it was given. They make unsupported answers…

Related roles in other families

Hiring nowKnowledge Graph EngineerKnowledge graphs and semantic systemsA Knowledge Graph Engineer builds linked records of the people, products and things a business cares about, each traced to its source. It gives AI…Hiring nowOntology EngineerKnowledge graphs and semantic systemsAn Ontology Engineer defines the concepts, relationships and rules that describe a business domain, so retrieval and AI systems return answers that…Hiring nowAI Knowledge ArchitectKnowledge graphs and semantic systemsAn AI Knowledge Architect designs how an application organises, governs and updates what it knows. That structure decides whether retrieval is…EmergingNeuro-Symbolic Knowledge EngineerKnowledge graphs and semantic systemsA neuro-symbolic knowledge engineer connects structured knowledge, such as ontologies and graphs, to learned models. The aim is answers that stay…

How we wrote this

Role definitions are our own editorial work, checked against occupational classifications, standards, research and employer pages. Titles vary by company, and this is a description of the work, not a job advert.

← Information retrieval and groundingAll new job families

Start a search

Hiring a Search Relevance Engineer?

Tell us the work. We find the people already doing it, whatever their job title says, and you meet them already interviewed for your role.