DescriptionCybersecurity is one of the highest growth areas within JPMorgan and has a unique opportunity to develop and deploy Machine Learning solutions that support Cyber Operations. A successful candidate must be comfortable working independently, have an understanding of data analysis, statistics, data engineering and the ability to develop predictive models that meet defined business outcomes.
As a Lead Security Engineer- Data Scientist in the Cyber Technology and Controls Product team, you will be will be part of a highly motivated team that focuses on analyzing data and creating and delivering Machine Learning solutions that will protect the firm from a variety of cyber-related threats.
Job responsibilities :
- Engage with cybersecurity domain experts to understand business goals and use cases related to using real-world data to solve business problems
- Work with cybersecurity engineers and data engineers to acquire data that addresses each use case (fraud, anomaly detection, Cyber threats)
- Perform Exploratory Data Analysis on datasets and communicate results to stakeholders
- Select statistical or Deep Learning models that are best positioned to achieve business results
- Perform feature engineering or hyperparameter tuning to optimize model performance
- Document measurements required to detect model or data drift in a Production setting
- Perform model governance activities for model interpretability, testability and results
Required qualifications, capabilities, and skills :
- Formal training or certification on Data Science concepts and 5+ years applied experience.
- Ability to perform Exploratory Data Analysis using Jupyter or SageMaker Notebooks
- Proficient in Pandas, SQL and Data Visualization tools such as Matplotlib, Seaborn or Plotly
- Working knowledge of probability, statistics and statistical distributions and their applicability to use cases
- Working knowledge of Scikit-Learn for development of classification, regression and clustering models
- Deep Learning frameworks such as Keras, Tensorflow or PyTorch
- Experience with classification and regression trees (Random Forest, XGBoost, AdaBoost)
- Experience with feature engineering complex datasets
- Possess the ability to explain model selection, model interpretability and performance metrics verbally and in writing.
Preferred qualifications, capabilities, and skills :
- Experience deploying Statistical or Machine Learning models in a production setting
- Experience with model monitoring and understanding data quality issues
- Experience creating synthetic datasets
- Development of REST APIs using tools such as Flask or FastAPI
- Working knowledge of Responsible AI, model fairness, and reliability and safety