About this role
Description <p>Do you want to teach a bank’s document engine to read?</p><p>Every mortgage application comes with a stack of documents: payslips, employer statements, valuation reports, bank statements and IDs. Our extraction engine automatically turns these documents into structured data that can be used throughout the lending process.</p><p>Making that engine smarter is one of <strong>Ohpen’s key objectives for 2026</strong>, as we move from classical extraction rules towards <strong>AI/LLM-based extraction</strong>.</p>As a <strong>Data Extraction Specialist – AI</strong>, you’ll help drive that transition end-to-end. You’ll configure and optimise the engine, build the LLM-based extraction that replaces existing rules, benchmark the results to prove extraction rate. Briefing Ohpen launched the world’s first <strong>cloud-native core banking platform</strong>. Within our <strong>Lending Suite</strong>, several components work together to process every document that comes in with a mortgage application:<ul><li><strong>DocStreet</strong> is our document processing platform. It receives, classifies and routes incoming documents.</li><li><strong>DTA2</strong> is the data extraction engine within DocStreet. It reads each document and turns it into structured fields, such as income, employer and property value, which our clients’ lending processes rely on.</li><li><strong>Orbis</strong> is the engine that executes automated validations on the extracted documents.</li></ul>You’ll join our <strong>Transformation & Innovation team</strong>, working within a small and focused data extraction squad. A small team means <strong>high ownership</strong> and plenty of opportunity to make an impact.<br><span style="font-size:15px;"><br></span><h2><span style="font-size:15px;">WHAT YOU WILL DO</span></h2><ul><li><strong>Improve extraction rates.</strong> Configure and tune DTA2 across different document types and fields, prioritising those that matter most to our clients.</li><li><strong>Roll out AI/LLM-based extraction.</strong> Design, build, evaluate and deploy LLM-based extraction within the engine. This includes everything from prompt design and model selection to guardrails, evaluation sets and production rollout.</li><li><strong>Prove that it works.</strong> Build and maintain the benchmarking loop that shows where extraction has improved, where it has regressed and why. No improvement ships without evidence.</li><li><strong>Improve the engine itself.</strong> Identify and implement engineering improvements across DocStreet, DTA2 and Orbis.</li><li><strong>Work closely with the people who use it.</strong> Collaborate with internal stakeholders across Product, Engineering and Lending Operations, as well as directly with our clients.</li></ul><br> About You <ul><li>You are <strong>analytically strong</strong>. You pick up new domains quickly and are comfortable being the person who figures out how things actually work.</li><li>You have a <strong>technical engineering background</strong>, with a degree in Computer Science, Software Engineering, Data Engineering or a comparable field, and <strong>1–5 years of hands-on experience</strong>.</li><li>You are <strong>AI-native</strong>. LLMs are a normal part of how you work. You know how to design and iterate on prompts and how to build benchmarks that show whether a change actually helped.</li><li>You are a <strong>proactive self-starter</strong>. In a small team, there is no one to wait for. You spot what needs doing, propose it and take ownership of getting it done.</li><li>You are a <strong>strong communicator</strong>. You can explain technical trade-offs to clients, respectfully challenge colleagues when needed and keep stakeholders informed without being asked.</li></ul><h2><span style="font-family:Arial, Helvetica, sans-serif;font-size:15px;">NICE TO HAVE</span></h2><ul><li>Experience with <strong>Java and AWS</strong>, as our engine runs on them.</li><li><strong>Dutch language skills</strong>, as most of the documents we extract are in Dutch.</li></ul> Why us? <ul><li>Ownership of a <strong>strategic 2026 objective</strong> from day one, in a team small enough that your work is visible to both clients and leadership.</li><li>The opportunity to move a <strong>production system used by regulated lenders from rule-based to AI-based extraction</strong>.</li><li>A role at the intersection of <strong>engineering, AI and the Dutch mortgage domain</strong>.</li><li><strong>Hybrid working</strong> from our office in the heart of Amsterdam.</li><li><strong>Competitive compensation and benefits</strong>.</li></ul>