Machine Learning Engineer
Role details
Job location
Tech stack
Job description
We're looking for a hands-on Machine Learning Engineer to join our Discovery team. A small, sharp group that's experimenting, prototyping, and pushing boundaries to help us take the next big leap in fraud prevention.
The opportunity
This is not your typical MLE role where you inherit a model and tweak hyperparameters. This is greenfield. You'll have the chance to shape the way we use AI across this product suite from early experiments to production-ready systems.
You'll collaborate with product, engineering, data scientists, and stakeholders to uncover fraud patterns, validate assumptions, and build the tech foundations of a product that will serve banks, protect people, and impact millions.
We're talking:
- Real-time signals
- Huge, noisy datasets
- Ethical, explainable AI
- And a whole lot of problem-solving
What you'll do
- Design and build ML pipelines from data ingestion to deployment
- Rapidly prototype models for fraud and AML use cases
- Work closely with Data Scientists and Product to test hypotheses and validate results
- Train and deploy models using TensorFlow, PyTorch, Scikit-learn, Spark (and Amazon SageMaker if you're into it)
- Design for interpretability and explainability because our users need to understand what the model's doing, not just trust it
- Implement automation and CI/CD for ML using modern MLOps practices
- Work hands-on with data infrastructure, storage, and cloud platforms (especially AWS)
- Contribute to building a scalable, secure, and responsible ML foundation
Requirements
Do you have a Master's degree?, You're not just great at writing code, you understand what it takes to bring machine learning into the real world. You like working in small, high-trust teams. You're resourceful, fast-moving, and thoughtful about how you build things. And you care about impact.
Must-haves
- Proven hands-on experience designing, building, and deploying ML models
- Deep knowledge of ML frameworks like TensorFlow, PyTorch, Scikit-learn, Spark
- Experience with data pipeline design, automation, and model lifecycle management
- Strong cloud experience (AWS preferred) You've shipped models in real environments
- Familiarity with CI/CD for ML, infrastructure as code, and containerised deployment
- You understand model interpretability and have a strong sense of ethical AI principles
- You're proactive, practical, and comfortable in ambiguity. You can turn an idea into a working prototype, fast
Bonus points
- Experience working in fraud, AML, or financial risk domains
- Familiarity with tools like FCRM, RiskShield, NICE Actimize, Pega
- Prompt engineering or LLM experimentation is a nice plus
- Strong Python chops, and comfort working across backend/data infra when needed
Benefits & conditions
- 8% holiday allowance + 8% personal benefits budget (use it on salary, training, or more time off)
- 25 holiday days + flexible working hours
- MacBook Pro, iPhone, and whatever else you need to build
- NS Business Card & travel cost coverage
- Hybrid setup
- Pension plan
- A high-trust team where you get space to own, experiment, and grow
- A flat culture, regular Friday drinks, and quarterly offsites with the whole company
Why now?
You'll be part of shaping something from day one. Building a system that helps banks catch fraud before it happens and keeps real people protected. We're early. We're moving fast. And we're looking for someone who wants to build not just models but something that matters.
If that sounds like you, let's chat.