Senior Machine Learning Engineer

Hello. We’re Teya.

Teya was founded on a simple belief: local businesses deserve better.

They are the cafés, restaurants, salons, shops and entrepreneurs that bring character to our high streets, create jobs and keep communities moving. Yet for too long, financial services has made life harder for them - with clunky tools, poor support and complexity that gets in the way of running a business.

Teya exists to change that.

We’re building a financial platform for local businesses across Europe - one built around simple tools, thoughtful design and real human support. Our Members rely on us to help them run their business with confidence, and that responsibility shapes the way we work.

We move fast. We care about quality. We stay close to the detail. And we believe great performance and genuine hospitality should go hand in hand.

If you want to build meaningful products, solve real problems and make a genuine difference for local businesses, we’d love to hear from you

Your Mission

As a Senior Machine Learning Engineer you will build the models and decision systems that turn Teya's data into better outcomes for our customers and our business. You will work on problems where quantitative rigor changes the result: who we onboard, how we detect and prevent fraud, how we price, and how we understand and grow customer value.

You'll join our AI Research & Development team, partnering with engineers, product managers, and domain experts to take problems from framing through model development and into reliable, monitored production systems. This role suits someone who combines strong statistical and machine learning foundations with the engineering discipline to ship, and who is motivated by measurable business impact rather than modeling for its own sake.

As a Senior Machine Learning Engineer at Teya, you will be expected to:

• Frame ambiguous business problems as well-posed modeling, inference, or optimization tasks, and choose methods that fit the data and the decision.

• Design, build, validate, and deploy predictive and decisioning models across areas such as fraud and risk monitoring, customer onboarding and due diligence, pricing, and customer lifetime value.

• Run rigorous experiments and causal analyses, including A/B testing, uplift modeling, and offline evaluation, to measure whether models actually move the outcomes that matter.

• Engineer features and build the data pipelines that feed training and serving, with attention to leakage, reproducibility, and data quality.

• Productionise models with strong attention to validation, backtesting, monitoring, drift detection, and retraining, so performance holds up after launch.

• Work closely with product managers, engineers, and domain experts to identify where modeling creates value and to integrate models into products and operational workflows.

• Apply optimization and operations research methods where decisions, not just predictions, are the goal.

• Contribute to modeling standards, evaluation practices, and reusable tooling across the team.

• Stay current with developments in machine learning and statistics, and apply new methods where they earn their place.

Requirements

• Strong foundations in statistics and machine learning, with the judgment to match methods to problems.

• Proficiency in Python and its data and ML ecosystem (for example pandas, scikit-learn, NumPy), and strong SQL.

• Hands-on experience building and deploying machine learning models in production, not only in notebooks.

• Solid command of supervised and unsupervised learning, including methods such as gradient boosting, regularised regression, and clustering, with a clear understanding of model evaluation and overfitting.

• Experience with experimentation and inference, including A/B testing and the basics of causal estimation.

• Experience with cloud platforms and modern engineering practices (CI/CD, APIs, monitoring, infrastructure as code).

• Strong software engineering fundamentals including testing, reproducibility, and maintainability.

• Ability to communicate quantitative findings and their business implications clearly to both technical and non-technical audiences.

Nice to have

• Experience building models in regulated industries such as payments, fintech, banking, risk, compliance, or fraud prevention.

• Experience with use cases such as:

• Fraud detection and anomaly detection

• Credit and onboarding risk decisioning

• Pricing and customer lifetime value modeling

• Churn and propensity modeling

• Forecasting and time series

• Recommendation and personalisation

• Background in operations research, mathematical programming, or stochastic optimization.

• Knowledge of MLOps, model lifecycle management, feature stores, monitoring, and governance.

• Experience with deep learning frameworks such as PyTorch or TensorFlow where the problem warrants them.

• Familiarity with data engineering concepts, analytics platforms, and experimentation frameworks.

• Contributions to the ML or statistics community through open source, research, or technical writing.

Teya is proud to be an equal opportunity employer.

We are committed to creating an inclusive environment where everyone regardless of race, ethnicity, gender identity or expression, sexual orientation, age, disability, religion, or background can thrive and do their best work. We believe that a diverse team leads to better ideas, stronger outcomes, and a more supportive workplace for all.

If you require any reasonable adjustments at any stage of the recruitment process whether for interviews, assessments, or other parts of the application—we encourage you to let us know. We are committed to ensuring that every candidate has a fair and accessible experience with us.