<h3>About Dwelly</h3> <p>Dwelly — a UK-based, AI-enabled lettings and property management platform, that is growing through a roll-up strategy acquiring estate agencies. The company leverages two arms: i) acquiring existing letting agencies, effectively buying its highly sticky, recurring revenue-type landlords portfolios, and then ii) building a top-notch technology to automate tenant management, payments, and post-rental property maintenance. The company seamlessly integrates AI services to automate all business processes within brick-and-mortar real estate agencies, integrating them into a tech-enabled digital letting platform in two months to radically improve the user experiences and increase efficiency of the business.</p> <p>We’re a fast-growing, product-focused company, backed by top-tier investors and led by a team with deep experience in real estate, technology, and operations.</p> <h3>Position Summary</h3> <p>We are looking for a <strong>Backend Engineer with strong applied ML experience </strong>to build production systems that extract, enrich, summarise and structure information from emails, documents and other unstructured data.<br>This is not a pure data science or research role. It is a production engineering role focused on building reliable Python backend services around NLP, retrieval and LLM-powered workflows.<br>You will work on practical problems such as extracting useful information from email correspondence during agency migrations and summarising a client’s full communication history inside their Dwelly profile.<br>The right person is comfortable working with messy real-world data, taking prototypes into production, measuring quality and improving systems through evaluation and feedback loops.</p> <h3><strong>What You’ll Do</strong></h3> <ul> <li>Build systems that extract structured data from emails, documents and other unstructured sources.</li> <li>Enrich migrated client, landlord, tenant and property records with useful information from communication history.</li> <li>Develop solutions that summarise a client’s full email history and surface the most relevant context inside Dwelly.</li> <li>Build production NLP / ML-backed backend services that work reliably on messy real-world data.</li> <li>Improve retrieval and ranking systems using approaches such as RAG, BM25, embeddings, hybrid search and reranking.</li> <li>Define quality metrics, evaluation datasets and feedback loops for extraction, summarisation and retrieval systems.</li> <li>Build Python backend services and APIs using frameworks such as FastAPI, Django, Flask or similar.</li> <li>Integrate ML and LLM workflows into production systems with clear error handling, observability and maintainability.</li> <li>Work closely with engineering, product and operations teams to turn real business problems into scalable automation systems.</li> </ul> <h3><strong>What We’re Looking For</strong></h3> <ul> <li>Strong Python backend engineering experience.</li> <li>Experience with API frameworks such as FastAPI, Django, Flask or similar.</li> <li>Production experience with NLP, ML, information extraction, retrieval, ranking or summarisation systems.</li> <li>Ability to take research ideas or prototypes into production.</li> <li>Strong understanding of evaluation, metrics and quality measurement for ML / LLM systems.</li> <li>Practical experience with retrieval systems such as RAG, BM25, embeddings, hybrid search or reranking.</li> <li>Comfortable working with messy, ambiguous or incomplete real-world data.</li> <li>Ability to build reliable services around ML workflows, including monitoring, testing and failure handling.</li> <li>Good understanding of LLM limitations, hallucination risks and safe user-facing AI.</li> <li>Strong ownership mindset and ability to work independently in ambiguous product areas. </li> </ul> <h3><strong>Nice to Have</strong></h3> <ul> <li>Experience building AI or LLM agents.</li> <li>Experience with document understanding, email parsing, entity extraction or CRM enrichment.</li> <li>Experience with LLM evaluation, prompt/version management or human-in-the-loop review workflows.</li> <li>Experience with vector databases or search infrastructure.</li> <li>DevOps or CI/CD experience for deploying ML-backed services.</li> <li>Experience testing ML systems on complex production datasets.</li> <li>Experience with typed programming languages such as TypeScript, Java, C#, C++, Kotlin, Scala or similar.</li> </ul> <h3><strong>What Success Looks Like</strong></h3> <ul> <li>Useful information can be extracted from emails and documents with measurable quality.</li> <li>Client communication histories can be summarised safely, clearly and with relevant context.</li> <li>Retrieval and ranking systems improve over time through evaluation and feedback.</li> <li>ML and LLM workflows are reliable, observable and production-ready.</li> <li>Operations and product teams can trust the outputs and understand when human review is needed.</li> <li>Unstructured data from acquired agencies becomes usable inside Dwelly faster and with less manual work.</li> </ul> <h3>Compensation & Benefits:</h3> <ul> <li>Fully remote role.</li> <li>Competitive compensation based on experience and impact.</li> <li>Opportunity to work on high-leverage automation systems at the intersection of backend engineering, applied ML, data and real operational workflows.</li> <li>Competitive salary with the potential for equity options based on performance, recognising exceptional contributions to our integration success.</li> </ul> <h3>What is it like being a Dwell-er?</h3> <p>Feel free to check out <a href="https://docsend.com/view/7v8gwrjaky7mn895">Dwelly Core Principles</a>. That’s about what we believe in, how we operate and make decisions.</p> <p>What we offer is not a fancy office or a static workplace. Instead, this is about solving one of the world’s most complex problems in the largest consumer industry in the world: reside