Senior Machine Learning Engineer

About Us at GoCardless

GoCardless is a global bank payment company. Over 100,000 businesses, from start-ups to household names, use GoCardless to collect and send payments through direct debit, real-time payments and open banking. 

GoCardless processes US$130bn+ of payments annually, across 30+ countries; helping customers collect and send both recurring and one-off payments, without the chasing, stress or expensive fees. We use AI-powered solutions to improve payment success and reduce fraud. And, with open banking connectivity to over 2,500 banks, we help our customers make faster, more informed decisions.

We are headquartered in the UK with offices in London and Leeds, and additional locations in Australia, France, Ireland, Latvia, Portugal and the United States.

At GoCardless, we're all about supporting you! We’re committed to making our hiring process inclusive and accessible. If you need extra support or adjustments, reach out to your Talent Partner — we’re here to help! 

And remember: we don’t expect you to meet every single requirement. If you’re excited by this role, we encourage you to apply!

The role 

GoCardless relies on machine learning to power features like payment intelligence and fraud detection.  We are expanding our ML capabilities to run models at scale - serving thousands of merchants and processing millions of payments monthly and also serving our internal data products.

 As a Senior Machine Learning Engineer, you’ll lead end-to-end model work and partner closely with Data Scientists, Data Engineers and other stakeholders.

What excites you 

• Architect & Design ML Solutions
• Own architecture for complex ML systems, selecting algorithms, frameworks and infrastructure to solve business problems at scale.
• Translate high-level product requirements into clear modeling objectives, aligning with GoCardless’s SLAs and business goals.
• End-to-End Model Development
• Partner with our Data Engineering team to ensure reliable data ingestion and preprocessing
• Collaborate with Data Scientists to design features 
• Build and maintain training workflows to train, tune and evaluate models.
• Establish reproducible experiment tracking (e.g., Vertex Experiments) for metrics, hyperparameters and model artefacts.
• Production Deployment & Monitoring
• Build and maintain scalable, automated pipelines for CI/CD of ML models.
• Deploy models as containerized services (Docker/Kubernetes, Vertex Endpoints)
• Define monitoring and alerting for model performance (drift detection, data quality checks) and collaborate with Data Scientists on model health and iteration.
• Cross-Functional Collaboration
• Engage with Product, Software Engineering and Design teams to inform roadmaps, surface technical feasibility, and prioritize ML initiatives 
• Liaise with Data Engineers to ensure data schemas, pipelines and validation processes meet ML workflow requirements.
• Leadership & Mentorship
• Set ML standards and best practices at GoCardless: establish coding guidelines, conduct design reviews, and evangelize solid ML principles (version control, testing, reproducibility).
• Mentor and coach mid-level and junior ML Engineers and Data Scientists, fostering a culture of continuous learning and high code quality.
• Innovation & Research
• Stay current on advances in machine learning and deep learning.
• Evaluate new tools and libraries across cloud platforms

What excites us  

• Experience & Education
• Bachelor’s or Master’s in Computer Science, Machine Learning, Statistics, Mathematics or equivalent. 
• 3+ years of hands-on experience designing, training and deploying production ML models - ideally on GCP Vertex AI or a similar managed platform.
• Track record of shipping and running  at least two end-to-end ML projects in production.
• Technical Skills
• Proficient in Python and SQL; familiarity with additional languages is a plus.
• Deep understanding of supervised and unsupervised learning methods and when to apply them.
• Extensive experience with ML frameworks (TensorFlow, PyTorch, scikit-learn), data processing tools and e