Job Title: Senior Data Scientist (AI / ML Engineer)
Salary: up to £135k (+ very generous early-stage equity, £100k+)
Location: Central London, EC1 (3 office day/week)
Company: B2B FinTech / Fraud Prevention
Employees: ~25
Funding: $15m+ (Series A)
This London startup is building a new intelligence layer designed to bring more context and security to digital payments. Their technology analyses transactions in real time, gathering signals from multiple sources to determine whether a payment is legitimate or potentially fraudulent.
The platform combines distributed data systems, real-time investigations and AI-driven decisioning to help financial institutions detect scams while allowing legitimate payments to flow without unnecessary friction. Within 2 years of being founded, they’re working with most Tier 1 banks and payment providers in the UK – and are just getting started!
They are now looking for an experienced Data Scientist (AI/ML Engineer) with deep fraud or financial crime experience (ideally APP fraud exposure) to join at an early stage and help shape the core intelligence powering the platform.
Key responsibilities:
- Designing and deploying machine learning models used to detect fraud and financial crime in payment flows
- Building features from heterogeneous data sources, including transaction data, contextual signals and unstructured information
- Improving systems that extract useful signals from fragmented or unstructured data sources
- Building reliable ML infrastructure to train, deploy and monitor models in production environments
- Working closely with product and engineering teams to ensure models improve real-world fraud outcomes
- Identifying the fraud signals, typologies and data sources that meaningfully improve detection capability
- Experimenting with both classical ML techniques and newer AI approaches where appropriate
- Helping shape data strategy, including how feedback loops and labelling pipelines are built to improve models over time
This role is focused on shipping production systems rather than academic research.
✅ Must have requirements:
- Strong practical experience building fraud detection systems or financial crime models in production
- Deep FinCrime / FinTech / Payments domain expertise
- Product mindset – focus on improving real-world outcomes, not just model metrics.
- Experience working in fast-moving environments where systems are built from scratch and priorities evolve quickly.
- Experience working with heterogeneous datasets (transaction data, enrichment signals, text, network signals etc.)
- Familiarity with model monitoring, drift detection and retraining pipelines
- Strong SQL and data engineering capability
- Strong programming skills in Python
Bonus points for:
- Exposure to / understanding of APP Fraud, payment fraud or transaction monitoring
- Previous experience working in an early stage start-up and/or high growth scale up
- Exposure to newer approaches such as LLM-powered systems
- Cloud infrastructure / data platforms experience, ideally GCP
…