About Cadence Cadence is a nutrition app built for the unique performance needs of active women. Our mission is to combat chronic undernourishment by delivering science-backed, AI-powered guidance through wearables, biomarkers, and behavior-driven insights. We’re building an experience that redefines performance optimization — beyond weight loss, beyond generic fitness tracking — personalized for the female body and lifestyle. Role Summary We’re looking for a Backend Data Engineer to own the data infrastructure and personalization engine that powers Cadence. This role will focus on embedding protocols, integrating AI workflows, and structuring data pipelines that support insights, gameplans, and adaptive feedback. You'll collaborate closely with our backend and product teams to translate biomarker data, user inputs, and activity tracking into dynamic nutrition recommendations. Key Responsibilities • Develop and deploy pipelines to embed nutrition protocols using OpenAI or similar LLM APIs • Implement vector search on MongoDB Atlas to support contextual recommendations • Design and manage collections and indexes for scalable vector queries • Collaborate with backend engineers to expose embedding search and inference results via API • Build logic for generating personalized insights (e.g., “what worked” nudges) based on check-in, wearable, and protocol data • Establish automated workflows for retraining or updating protocol logic as new inputs arrive • Contribute to performance analytics: behavioral tracking, plan adherence, user trends • Support secure handling of sensitive data and system reliability best practices Our Tech Stack • iOS Frontend: Swift (UIKit), Apple HealthKit • Backend APIs: Node.js (Express), Python (FastAPI) on Heroku • Database: MongoDB Atlas, including vector DB for AI insights • Authentication: Auth0 • Payments: Stripe via webhook • AI + Vector Search: OpenAI and MongoDB Embeddings • CI/CD: GitHub with manual deploys (CI optional) • Analytics: Mixpanel, Sentry (planned for crash/error tracking) Ideal Candidate • 4+ years of experience in data engineering or machine learning engineering • Strong proficiency in Python, REST API development, and data modeling • Experience with OpenAI or other embedding-based NLP systems • Familiarity with vector databases (Pinecone, MongoDB Atlas, FAISS, etc.) • Skilled at working with semi-structured data (e.g., user profiles, check-ins, wearable data) • Understanding of metrics design: engagement, adherence, feedback loops • Bonus: Experience in health, wellness, or personalization engines • Bonus: Familiarity with fast-paced startup workflows and MVP-first thinking Why Cadence? • Help architect the personalization engine behind a mission-driven product • Work with a lean team where your work directly impacts the end-user experience • Tackle real-world data challenges at the intersection of AI, nutrition, and women’s health • Flexible, async-friendly team with deep respect for craft and impact