Search Relevance Engineer - REMOTE UK/US/EU
About the role
We are looking for an experienced Search Relevance Engineer to help shape and optimise the search experience for millions of users. This role sits at the intersection of engineering and data science, focusing on search relevancy, ranking models, and query understanding. You will work closely with Product, Engineering, DevOps, and Data teams to design and deliver strategic projects that directly impact customer experience.
What you’ll be doing
* Fine-tuning keyword search (including BM25), query expansion, and retrieval methods (ANN dense retrieval, sparse retrieval, semantic search).
* Applying techniques such as entity/name density recognition, query understanding, query rescorers, and learning-to-rank models.
* Experimenting with embeddings and vector search to improve personalisation and semantic relevance.
* Running offline evaluations to test and validate search performance improvements.
* Creating APIs to integrate custom ML models for reranking, personalisation, and visual merchandising.
* Optimising indexes and experimenting with analyzers to improve stability and performance.
* Collaborating cross-functionally with Product, ML Engineers, and Data Scientists to deliver scalable solutions.
* Mentoring team members and promoting a culture of engineering excellence and continuous improvement.
What we’re looking for
* Strong development skills across Python and MySQL.
* 5+ years of hands-on experience developing with Elasticsearch, with proven expertise in relevance engineering.
* Demonstrable use of ELK stack tools in production environments.
* Experience creating and deploying APIs in production (e.g. FastAPI).
* Solid understanding of database architecture and design.
* A strong test-and-learn mindset, with experience in offline evaluation methods.
* Excellent problem-solving skills, strategic thinking, and the ability to communicate effectively with both technical and non-technical stakeholders.
* Fluent in spoken and written English.
Nice to have
* Experience with embeddings and vector databases.
* Direct collaboration experience with Machine Learning Engineers or Data Scientists.