Staff Applied ML Engineer - Financial Crime

Wise
London
Workplace: HybridFull timeGBP 145,000 - 182,000 annuallyFunction: Data Science & Machine LearningSkills: ["Architectural decision-making","Mentorship","Independent problem solving","Technical strategy influence"]

Design and ship deep learning and ML models for financial crime detection, including sequence-, graph-, and attention-based approaches that support real-time decisions at Wise’s scale. Own the architecture strategy across model families, serving patterns, and training paradigms, and build reusable end-to-end pipelines from experimentation to production. Prototype foundation model embedding approaches, partner with Data Science on evaluation/causal measurement, and mentor engineers and scientists.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Wise
Wise
3 days ago

Staff Applied ML Engineer - Financial Crime

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 6 hours agoStatus: Live
Reposted: similar role first listed 2 months ago

Job Summary

Design and ship deep learning and ML models for financial crime detection, including sequence-, graph-, and attention-based approaches that support real-time decisions at Wise’s scale. Own the architecture strategy across model families, serving patterns, and training paradigms, and build reusable end-to-end pipelines from experimentation to production. Prototype foundation model embedding approaches, partner with Data Science on evaluation/causal measurement, and mentor engineers and scientists.
Location: London
Workplace: Hybrid
Employment Type: Full time · Permanent
Job Function: Data Science & Machine Learning
Seniority: Mid level

Key Responsibilities

  • •Design and ship ML and deep learning models for financial crime detection that support real-time decisions at Wise’s scale.
  • •Define the architecture strategy for how Wise applies ML to risk, including model families, serving patterns, and training paradigms.
  • •Build reusable end-to-end pipeline patterns from experimentation through training to production deployment.
  • •Evaluate and prototype foundation model and embedding approaches for transaction representation across FinCrime domains.
  • •Partner with Data Science on model evaluation, experimentation design, and causal measurement where clean A/B testing isn’t possible.

Pay and Benefits

Salary: GBP 145,000 - 182,000 annually
Equity and Bonus:Equity
Perks:Rsus

Key Requirements

  • •Production experience shipping deep learning models at scale with systems serving real traffic under latency constraints.
  • •Ability to make architecture-level decisions independently, including model selection, training infrastructure, and serving strategy with clear tradeoffs.
  • •Experience designing ML systems with hard latency/throughput constraints, including optimization choices like quantization, pre-computed embeddings, and batching strategies.
  • •Strong fundamentals in deep learning, including gradient dynamics, attention mechanisms, graph message-passing, and sequence modeling.
  • •Python experience with PyTorch (or equivalent) plus distributed training and ML pipeline orchestration.
Experience:Financial services
Skills:Architectural decision-makingMentorshipIndependent problem solvingTechnical strategy influence
Languages:English (UK)
Tech Stack:PythonPyTorchDeep learningGraph neural networksFoundation modelsLLM evaluationDistributed trainingML pipeline orchestrationQuantizationPre-computed embeddingsBatching strategiesA/B testingAttention mechanismsGraph message-passingSequence modeling

Company Brief

Wise
Wise (formerly TransferWise) is a London-based fintech that provides low-cost international money transfers, multi-currency accounts and payment infrastructure for individuals and businesses worldwide.
Industry: Payments
Company Size: Enterprise (1,001+ employees)
Revenue: USD 1B+
Growth: Public Company
Valuation: Public Company (Market Cap in USD)
Funding: IPO / Publicly Listed
Headquarters: London, United Kingdom
Founded: 2011
Glassdoor
Glassdoor: 3.8
WebsiteLinkedInGlassdoor