Personalised Search & Retrieval Engineer (Agentic Commerce)
Location: London (In Person)
About Swap
Swap is the infrastructure behind modern agentic commerce. The only AI-native platform connecting backend operations with a forward-thinking storefront experience.
Built for brands that want to sell anything - anywhere, Swap centralizes global operations, powers intelligent workflows, and unlocks margin-protecting decisions with real-time data and capability. Our products span cross-border, tax, returns, demand planning, and our next-generation agentic storefront, giving merchants full transparency and the ability to act with confidence.
At Swap, we're building a culture that values clarity, creativity, and shared ownership as we redefine how global commerce works.
What you will do
* Own Semantic Search Quality: Design and optimise embedding models, chunking strategies, and indexing approaches to ensure high-quality semantic understanding and retrieval across diverse content types.
* Build Personalisation Systems: Integrate user-level signals, behavioural patterns, and preference data into search algorithms to deliver contextually relevant and personalised results.
* Design Reranking & Relevance Models: Combine BM25, dense retrieval, and learning-to-rank approaches. Build sophisticated reranking algorithms that incorporate relevance signals, user context, and business objectives to optimise search result ordering.
* Create Evaluation Frameworks: Develop comprehensive evaluation systems including offline metrics, online A/B testing, and user satisfaction measurements to continuously assess and improve search performance.
* Optimise Performance & Scale: Tune latency and throughput across the entire search pipeline, working with vector databases and distributed systems to ensure sub-second response times.
* Build Agentic Integrations: Design retrieval systems that provide accurate context for AI applications, ensuring responses are well-grounded in relevant, up-to-date information.
* Implement Continuous Learning: Create feedback loops that capture user interactions, click-through rates, and engagement signals to continuously refine personalisation algorithms.
Skills & Qualifications
* 4+ years of experience in search engineering, information retrieval, with proven track record of improving search quality at scale.
* Deep expertise in semantic search technologies including embedding models, vector databases (postgres, pgvector), and modern retrieval architectures.
* Strong knowledge of search fundamentals: BM25, TF-IDF, learning-to-rank algorithms, and experience with search evaluation metrics (NDCG, MRR, MAP).
* Hands-on experience with machine learning frameworks (PyTorch, TensorFlow), search libraries, and modern ML infrastructure.
* Proficiency in Python, SQL, and distributed computing with experience building high-throughput, low-latency systems.
* Experience with personalisation techniques, collaborative filtering, and integrating user behaviour signals into ranking algorithms.
* Knowledge of A/B testing methodologies, statistical analysis, and search analytics for continuous optimisation.
* Familiarity with modern AI/ML operations, model deployment, and monitoring in production environments.
Benefits
* Competitive base salary.
* Stock options in a high-growth startup.
* Competitive PTO with public holidays additional.
* Private Health.
* Pension.
* Wellness benefits.
* Breakfast Mondays.
Diversity & Equal Opportunities
We embrace diversity and equality in a serious way. We are committed to building a team with a variety of backgrounds, skills, and views. The more inclusive we are, the better our work will be. Creating a culture of equality isn't just the right thing to do; it's also the smart thing.