Develop Statistical, Machine Learning and Deep Learning solutions to tackle fraud and risk
Manage the end-to-end model lifecycle including real-time model serving
Build and use data pipelines to extract and communicate meaningful insights from large datasets
Conduct data-backed experiments and analyses to and fine-tune model performance across a variety fraud MOs and enterprise use cases
Contribute to developing production-grade software applications backed by statistics and ML
What you bring
BS, MS or Ph.D in Machine Learning, Computer Science, Mathematics, Statistics or other quantitative disciplines. Experience in Machine Learning Engineering or Data Science roles.
Proficiency in Python and scaling out to the cloud (AWS/Databricks/Azure)
Strong familiarity with SQL, data modelling (preferably DBT), distributed analytic processing technologies (Athena, Big Query) and visualization platforms (Superset, Looker, Tableau)
Proven expertise in writing production code and deploying DS/ML applications, preferably in fintech fraud, risk, payments or compliance
Prior experience in building ML observability to uphold the performance and reliability of ML models in production
Skilled in Exploratory Data Analysis to investigate ad-hoc questions and explain anomalous data
Some familiarity writing backend code and experience with Golang and efficient containerization using Kubernetes, Docker etc., is a plus
Advanced expertise in software engineering principles
Creativity in building data science solutions in the absence of feedback or labelled data
Ability to thrive in an unstructured environment, working autonomously on a strong team to find opportunity and deliver business impact.
