ML Engineer - Statistical Integrity (Financial Crime)

Requirements:

• Education: A degree in STEM (Computer Science, Mathematics, Statistics, Physics, Chemistry, Electrical Engineering, or a related quantitative field).
• Statistical Integrity: Strong mathematical and statistical fundamentals with a proven track record of applying statistical analysis to complex data environments.
• ML Lifecycle Expertise: Hands-on experience working across model training, evaluation, and deployment (utilizing frameworks around Machine Learning, AI, Neural Networks, or NLP).
• Programming Skills: Strong proficiency in Python or Java for data scripting and production engineering, alongside advanced SQL capability.
• Data Fundamentals: Solid hands-on experience building static data pipelines, conducting deep-dive data analysis, and using data visualization tools to understand statistical behavior.

Nice to Have:

• Proven success in competitive machine learning environments or platforms (e.g., Kaggle, KDD competitions, or Google Summer of Code / GSoC).
• Experience with specialized ML architectures such as Graph Neural Networks (GNNs), Support Vector Machines (SVM), Natural Language Processing (NLP), or Transformers/LSTMs.
• Familiarity with real-time streaming data pipelines (e.g., Kafka).
• Domain experience within Fintech, E-commerce, or fast-scaling tech companies.

What You'll Be Doing:

• Building, scaling, and maintaining the integrity layer of our label platform for Risk ML models.
• Defining, implementing, and monitoring statistical fundamentals and key quality metrics for data and labels.
• Designing automated audit processes to evaluate and monitor label quality over time.
• Working end-to-end on machine learning model training, evaluation, and pipeline deployment.
• Collaborating closely with cross-functional partners across Risk Intelligence, Data Engineering, and Product.