This role tunes anti money laundering and fraud detection models on live customer transaction data, weighing detection gains against alert volume. A strong candidate has several years of customer facing data science work in financial crime, can dig into missed cases and pattern drift, and can explain and defend tuning choices to compliance teams and regulators. Judgment about when a model change is safe matters as much as technical skill.
How it fits the AI era
The models here blend rules with explainable AI, so the work is less about building models from scratch and more about adapting and justifying them on real data. AI speeds up analysis and pattern finding, but explaining why an alert fired and standing behind that reasoning with a customer stays human. Regulatory defensibility and sign off discipline remain firmly in people's hands.
How it builds AI experience
Working on explainable detection models for banks, payment firms and crypto companies builds practical skill in tuning AI systems under real compliance constraints. A candidate can strengthen this by studying transaction monitoring typologies, false positive economics, and how hybrid rules plus AI detection is validated and documented for audits.
Worth showing
- AML or fraud analytics
- Customer facing data science
- Python and SQL
- Model and threshold tuning
- Explaining models to stakeholders
This is our own read, written from the employer's posting and the company's Spotlight. The employer's posting is the source of truth for the role.
About Hawk AI
Hawk provides AI-powered anti-money laundering, screening, and fraud prevention technology for banks, payment companies, neobanks, fintechs, and cryptocurrency firms, per the company.
#J-18808-Ljbffr