One of the companies we work with at Joppy, a TOP Fintech, is looking for a Data & Machine Learning Engineer to join the team.

Working arrangement: HYBRID in Barcelona (3 days a week in the office)

Our company is an end-to-end working capital solutions provider focused on enabling CFOs/Finance teams of SMEs to pay their suppliers and collect from their customers. This includes short-term credit (factoring, supply chain finance and loans) and payment automation solutions.

We are looking for a Data Engineer with a strong product mindset to join our Data team. Your primary mission will be to design, build, and maintain production-grade data products that power our credit workflows — turning Data Scientist research and models into robust, scalable services that enable real-time decisions at the core of our business.

What will you own?

You will be the bridge between Data Science and Engineering. Your day-to-day will be grounded in building data products/services that directly enable credit and fraud decisions — not just moving data, but shaping it into services, models, and systems that internal users trust and rely on.

In order to achieve your mission, you will:

Productionize credit risk and fraud models

- Work closely with the Data Science team to productionize Data Science solutions
- Own the full ML lifecycle: feature engineering, training and retraining workflows, model versioning (MLflow), and live monitoring for drift and degradation.
- Ensure deployed models meet the performance and latency standards required by automated credit decision workflows.

Design and deliver data services and products

- Build internal APIs to expose credit scoring, risk signals, and underwriting features — consumed by the company's platform, operational teams, and third-party partners.
- Model and maintain database schemas for credit products: scoring results, decision logs, exposure tracking, repayment history — optimized for both operational and analytical access.
- Own the data layer for new products (micro-credit, portfolio factoring,



supply chain finance) from scratch: define the business logic, model the data, and implement end-to-end pipelines.

Build for scalability and reliability

- Design systems that grow with credit volumes and new product types — without requiring hard architectural rework every time.
- Apply software engineering best practices: modular code, unit and integration tests, CI/CD pipelines, clear documentation.
- Containerize and deploy services on AWS with Docker; orchestrate batch workflows (scoring runs, data refresh) with tools like Airflow.

Collaborate closely across teams

- Data Scientists: iterate rapidly on productionization — you are their engineering partner, not just a deployment step.
- Software Engineers: integrate data services into the platform cleanly, with clear API contracts and stable interfaces.
- Credit, Risk and Underwriting teams: translate operational needs into robust data product requirements.
- In doing so, you will contribute to the achievement of XXXXX’s long-term growth plans

Your skills:

- End-to-end ML & data engineering — You have at least 3 years of experience in shipping Data Science solutions into production: feature pipelines, training and retraining workflows, model versioning, and live monitoring. Not prototypes — real systems that users and workflows depend on.
- Python & modern data frameworks — Clean, modular, testable Python is your default. Comfortable with FastAPI, SQLAlchemy, Pydantic and similar libraries; you know the difference between code that works and code that ships.
- Data services & APIs — Hands-on building internal REST APIs: request validation, async patterns, error handling,



OpenAPI docs. You design stable contracts and think about versioning and performance from day one.
- Data modeling & SQL — Strong database skills across operational and analytical workloads: schema design, indexing, partitioning, query optimization. Comfortable modeling finance-domain data — scoring outputs, decision logs, exposure and repayment history.
- Cloud & infrastructure — Solid AWS cloud experience (S3, RDS, EC2, Lambda, IAM, others) deploying and operating APIs and batch workers. Comfortable containerizing workloads with Docker.
- Ownership & business acumen — Small team, high autonomy. You drive work from problem definition to production with minimal guidance, and you measure quality in terms of credit decisions — not just technical correctness.

What can we offer you?

- Full-time work with an open-ended contract
- Hybrid work model: we work 3 days from the office and 2 days from home to improve work-life balance
- Adaptable benefits with Coverflex: you will be able to include in your paycheck the monthly expenses for food, transportation, daycare and others
- Medical insurance: we offer an optional health insurance through Sanitas, with competitive rates and company subsidizes 30% to guarantee your wellbeing
- Communicate better with your colleagues by signing up for free English or Spanish classes if you need them
- Gym membership with Urban Sports Club, partly subsidized by company (we also have a running club!)
- Incredible and highly motivated co-workers
- You will participate in our company events and get to meet the rest of the team that is spread across Spain
- You will be part of our dynamic and international work environment, with a flat hierarchy and open communication between teams
- Library with plenty of books to choose from. If you can't find anything, let us know and we'll add it to the library.
- Free fruit, coffee and tea in the office. We know it's customary, but we like to take care of you anyway.

📌 Mid Data & Machine Learning Engineer (Barcelona)
🏢 Joppy
📍 Barcelona