Data Science Lead - AML Risk

Requirements:

• Experience implementing, training, testing and evaluating performance of Machine Learning systems
• Strong Python knowledge. A big plus for proven familiarity and experience with OOP principles
• Experience with statistical analysis, and ability to produce well-designed experiments
• A strong product mindset with the ability to work independently in a cross-functional and cross-team environment
• Good communication skills and ability to get the point across to non-technical individuals
• Strong problem solving skills with the ability to help refine problem statements and figure out how to solve them

Nice to Haves:

• Familiarity with automating operational processes via technical solutions, for example Large Language Models
• Willingness to get hands dirty with operational side by sides to understand their pain points
• Knowledge and experience within the Financial Crime domain

What you'll be doing:

• AML Risk Detection System Development
  • Developing efficient and effective AML detection controls using a mixture of unsupervised, semi-supervised and supervised learning with GenAI
  • Creating frameworks to prove controls coverage at a regional level
  • Developing technologies to serve Wise's diverse international user base
• Building a team of high performing specialists
  • Working with product managers and engineering leads to understand staffing requirements
  • Hiring specialists
  • Mentoring more junior members of the team on technical and non-technical skillsets
• Performance Testing and Optimisation
  • Evaluating our AML systems against internal and external benchmarks
  • Developing decisioning layers to find optimal trade-offs between precision and recall
  • Providing data-driven insights on potential outcomes under various scenarios
• Operational Process Development
  • Collaborating with operational teams to refine processes, ensuring effective feedback integration into our automation systems
  • Designing and managing projects that utilise excess operational capacity, such as manual data labelling for model improvement
  • Creating systems which provide in-depth insight to investigators on red flags and typologies present on profiles/transactions
• Deployment and Implementation
  • Packaging algorithms into deployable libraries/objects and transitioning them from staging to production environments
  • Implementing and maintaining scheduled processes for data gathering and model retraining using automated pipelines
  • Maintaining production-grade Python services

Perks and Benefits:

No specific perks and benefits mentioned in the job description.