About this role
Your mission Are you passionate about technology with a purpose? Want to make a meaningful impact on people's health? Want to work in an AI-native company? At Relu, we're growing - and we're looking for someone like you.<br><br>We're looking for a Backend Engineer, Integrations & Applied AI to join our Automate Platform team. You'd own the inbox pipeline from the moment a case arrives: get data in from every scanner and folder, understand the case, act on it, and keep the dentist in the loop. What you would work on:<ul><li><strong>Integrations in:</strong> scanner platforms (3Shape, Medit, iTero, Shining3D, AlliedStar, DS Core, Dexis and new ones), folder sync, email, WeTransfer.</li><li><strong>Integrations out: </strong>LMSs (Labtrac, DentiSky and others) for pulling order data and pushing status, CAM and printers (Shapeware, Formlabs, SprintRay, Carbon), folder sync out, exports to 3Shape and Exocad.</li><li><strong>Automatic case entry: </strong>enter scanner data into the LMS. For LMSs without an API, a browser or computer-use automation.</li><li><strong>Rx digitizer: </strong>read prescription PDFs and scanned forms into structured data (teeth, shades, materials, due dates), across languages and lab abbreviations.</li><li><strong>Rx intelligence: </strong>from the Rx, notes, doctor and the lab's history, predict which CAD orders to create, and learn from what users accept or correct.</li><li><strong>Rx QC: </strong>flag missing, inconsistent or contradictory prescriptions.</li><li>Scan Check in the inbox (backend): pick checks by order type, set blocker versus warning. The AI team builds the checks.</li><li><strong>Dentist messaging: </strong>per-case threads through scanner platforms, email and WhatsApp.</li><li><strong>Ask Relu: </strong>tools that act in the app, the knowledge base, model choice and cost, answer-quality evals.</li></ul><br><strong>First 6 months</strong><ul><li>Month 1: take over inbox poll health and two or three vendor integrations. Fix the known evidence leaks in the sync templates.</li><li>Months 2 to 3: build the Rx extraction eval set from real cases. Ship the digitizer and normalization v2 behind a confidence threshold.</li><li>Months 3 to 5: first LMS integration (pull data, push status), then automatic case entry for one LMS.</li><li>Months 5 to 6: Rx intelligence v1, predicting CAD orders per lab and learning from corrections.</li></ul> Your profile <strong><span style="font-family:Verdana, Geneva, sans-serif;">Must-haves</span></strong><span style="font-family:Verdana, Geneva, sans-serif;"><br></span><ul><li><span style="font-family:Verdana, Geneva, sans-serif;">Product ownership and vision: takes a raw user problem ("a lab says cases are missing", "order entry takes too long"), finds the real need, and scopes what is essential versus nice to have before building.</span></li><li><span style="font-family:Verdana, Geneva, sans-serif;">3+ years of backend engineering, strong Python.</span></li><li><span style="font-family:Verdana, Geneva, sans-serif;">Has built many third-party integrations and handled OAuth and token refresh, rate limits, idempotency, retries, webhooks versus polling, and schema drift.</span></li><li><span style="font-family:Verdana, Geneva, sans-serif;">Has shipped LLM features to production with evals: datasets, metrics, regression checks when prompts or models change, cost tracking.</span></li><li><span style="font-family:Verdana, Geneva, sans-serif;">Owns problems end to end, from "a lab says cases are missing" to root cause, fix and monitoring.</span></li><li><span style="font-family:Verdana, Geneva, sans-serif;">Pragmatic: picks a rules catalog with an LLM fallback over an elaborate ML system when that works.</span></li></ul><br><span style="font-family:Verdana, Geneva, sans-serif;"><strong>Nice-to-haves</strong></span><ul><li><span style="font-family:Verdana, Geneva, sans-serif;">Healthcare, dental or regulated-data experience (HIPAA, GDPR).</span></li><li><span style="font-family:Verdana, Geneva, sans-serif;">Document extraction or OCR, or browser and computer-use automation.</span></li><li><span style="font-family:Verdana, Geneva, sans-serif;">Workflow engines (ActivePieces, Temporal, n8n) or ETL pipelines.</span></li><li><span style="font-family:Verdana, Geneva, sans-serif;">Dutch or French.</span></li></ul> Why us? <ul><li style="font-family:Verdana, Geneva, sans-serif;">A mission that matters: we're improving dental care and making higher-quality dentistry accessible to everyone, globally</li><li style="font-family:Verdana, Geneva, sans-serif;">A fast-growing company where your growth goes hand-in-hand with ours — real impact, real ownership, early responsibility and skills in the technologies of the future</li><li style="font-family:Verdana, Geneva, sans-serif;">The chance to work with the latest AI technologies and industry leaders in dentistry</li><li style="font-family:Verdana, Geneva, sans-serif;">Fun team culture: after-works, bi-weekly sports, hackathons, retreats</li></ul>