Senior Data Scientist
<p><b>Salary: £75,000 - 95,000 per year</b></p>
<b>Requirements:</b>
<ul><li>Strong experience shipping applied ML into production (not just experimentation)</li><li>Strong Python + ability to write maintainable, tested code</li><li>Strong SQL + comfort working directly with messy, high-volume data</li><li>Solid modelling judgement: calibration, leakage, bias, thresholding, cost trade-offs, monitoring/drift</li><li>Experience building decisioning systems where reliability, latency, and explainability matter</li><li>Experience in fraud/scams, payments, risk, trust & safety, AML, or adjacent domains (nice-to-have)</li><li>Familiarity with graph/network features and entity resolution style problems (nice-to-have)</li><li>Experience with MLOps tooling (model registry/MLflow, feature stores, orchestration) (nice-to-have)</li><li>Comfort with cloud-native/event-driven systems and working closely with platform/backend engineers (nice-to-have)</li><li>Experience integrating unstructured signals (text/embeddings/RAG style pipelines) into decision systems (nice-to-have)</li></ul>
<b>Responsibilities:</b>
<ul><li>Build and ship scam risk models and signals (typology classification, risk scoring, decision logic)</li><li>Engineer features across heterogeneous data: transaction context, behavioural sequences, counterparty signals, network/graph patterns, and unstructured evidence</li><li>Design calibrated outputs (scores + reason codes) that are actionable and explainable for banking workflows</li><li>Own evaluation end-to-end: leakage avoidance, cost-sensitive metrics, thresholding, phased rollouts, and post-incident learning</li><li>Productionise ML: packaging, deployment, monitoring, drift detection, and retraining strategies</li><li>Collaborate closely with backend/product teams to integrate intelligence into real-time payment flows</li><li>Work alongside agent/LLM workflows for evidence gathering and synthesis, while keeping the decision core predictable and auditable</li></ul>
<b>Technologies:</b>
<ul><li>Backend</li><li>Cloud</li><li>Flow</li><li>LLM</li><li>Network</li><li>Python</li><li>SQL</li><li>Security</li><li>AI</li></ul>
<p><b>More:</b></p>
<p>We are a high-growth fintech company building a payment intelligence layer for banks, focused on running real-time investigations on payments to provide rich context on counterparties and situations. Our goal is to intercept scams while ensuring genuine payments flow smoothly. We are at an early stage, moving fast, and tackling problems where correctness, security, and reliability are non-negotiable. Join us for a mission with real-world impact, work on real-time, bank-grade ML systems, and enjoy high autonomy with meaningful technical decisions in a London hybrid work environment. Visa sponsorship is also available.</p>
<p>last updated 8 week of 2026</p>
<b>Requirements:</b>
<ul><li>Strong experience shipping applied ML into production (not just experimentation)</li><li>Strong Python + ability to write maintainable, tested code</li><li>Strong SQL + comfort working directly with messy, high-volume data</li><li>Solid modelling judgement: calibration, leakage, bias, thresholding, cost trade-offs, monitoring/drift</li><li>Experience building decisioning systems where reliability, latency, and explainability matter</li><li>Experience in fraud/scams, payments, risk, trust & safety, AML, or adjacent domains (nice-to-have)</li><li>Familiarity with graph/network features and entity resolution style problems (nice-to-have)</li><li>Experience with MLOps tooling (model registry/MLflow, feature stores, orchestration) (nice-to-have)</li><li>Comfort with cloud-native/event-driven systems and working closely with platform/backend engineers (nice-to-have)</li><li>Experience integrating unstructured signals (text/embeddings/RAG style pipelines) into decision systems (nice-to-have)</li></ul>
<b>Responsibilities:</b>
<ul><li>Build and ship scam risk models and signals (typology classification, risk scoring, decision logic)</li><li>Engineer features across heterogeneous data: transaction context, behavioural sequences, counterparty signals, network/graph patterns, and unstructured evidence</li><li>Design calibrated outputs (scores + reason codes) that are actionable and explainable for banking workflows</li><li>Own evaluation end-to-end: leakage avoidance, cost-sensitive metrics, thresholding, phased rollouts, and post-incident learning</li><li>Productionise ML: packaging, deployment, monitoring, drift detection, and retraining strategies</li><li>Collaborate closely with backend/product teams to integrate intelligence into real-time payment flows</li><li>Work alongside agent/LLM workflows for evidence gathering and synthesis, while keeping the decision core predictable and auditable</li></ul>
<b>Technologies:</b>
<ul><li>Backend</li><li>Cloud</li><li>Flow</li><li>LLM</li><li>Network</li><li>Python</li><li>SQL</li><li>Security</li><li>AI</li></ul>
<p><b>More:</b></p>
<p>We are a high-growth fintech company building a payment intelligence layer for banks, focused on running real-time investigations on payments to provide rich context on counterparties and situations. Our goal is to intercept scams while ensuring genuine payments flow smoothly. We are at an early stage, moving fast, and tackling problems where correctness, security, and reliability are non-negotiable. Join us for a mission with real-world impact, work on real-time, bank-grade ML systems, and enjoy high autonomy with meaningful technical decisions in a London hybrid work environment. Visa sponsorship is also available.</p>
<p>last updated 8 week of 2026</p>