Cybersecurity AI/ML Lead - Data Scientist

As a Lead Security Engineer - Data Scientist at JPMorgan Chase within the Cybersecurity & Technology Controls, you will be an integral part of a team that develops advanced analytical and machine learning solutions to address complex cybersecurity and technology risk challenges. As a core technical contributor, you will help design and deliver scalable, auditable, and data-driven solutions that support our Cyber Operations teams.

You'll be conducting data analysis, statistical modeling, machine learning, and deep learning techniques to solve cybersecurity and technology risk problems. You will be able to prepare and analyze complex datasets, develop and evaluate models, and communicate findings clearly to technical and business stakeholders. You'll understand when Generative AI, transformer architectures, and related techniques are appropriate for applied security use cases.

Job responsibilities

• Partner with stakeholders, business leaders, cybersecurity engineers, and data engineers to understand security needs, define use cases, and acquire the data required to address them.
• Perform exploratory data analysis on security and technology datasets, identify meaningful patterns, and communicate findings to stakeholders.
• Select, develop, and evaluate statistical, machine learning, deep learning models that are appropriate for cybersecurity use cases and business outcomes.
• Prepare model-ready datasets through feature engineering, data quality assessment, and other data preparation techniques.
• Leads reuse-first adoption of enterprise-authorized AI capabilities within the work environment to accelerate data architecture and model analysis and strategic decisioning, with human-in-the-loop validation and appropriate handling of sensitive data.
• Establishes portfolio-level guardrails for AI-assisted and agentic workflows used in data engineering design and delivery, including traceability/auditability and control expectations aligned to resiliency and security standards.
• Support model governance by documenting model selection, interpretability, testability, performance, limitations, and results.
• Design, build, review, debug, and maintain secure, high-quality production code for analytical and machine learning solutions.
• Contribute to security control effectiveness by applying industry insights, internal standards, and regulatory expectations to improve security processes and protocols.
• Add to a team culture of diversity, equity, inclusion, and respect.

Required qualifications, capabilities, and skills

• Obtain 5 plus years of experience with formal training or certification in security engineering concepts
• Working knowledge of probability, statistics, statistical distributions, and their application to cybersecurity or technology risk use cases.
• Advanced Python skills, including Pandas, SQL, and data visualization tools such as Matplotlib, Seaborn, or Plotly.
• Experience leading teams in the safe use of enterprise-authorized AI capabilities within the work environment for security engineering workflows, including validation habits and awareness of data sensitivity.
• Ability to review and validate AI-assisted security recommendations before adoption, escalating uncertainty and ensuring outcomes align to security, resiliency, and auditability expectations.
• Experience using notebooks such as Jupyter, SageMaker, or VS Code to analyze data, document methods, and communicate results.
• Working knowledge of Scikit-Learn for classification, regression, and clustering models, plus machine learning or deep learning frameworks such as PyTorch.
• Experience preparing complex datasets for modeling, including data cleaning, feature engineering, and data quality assessment.
• Ability to explain model selection, interpretability, performance metrics, and limitations verbally and in writing.
• Proficiency with Software Development Life Cycle, CI/CD practices, application resiliency, and secure software delivery.
• In-depth knowledge of the financial services industry and related IT systems.

Preferred qualifications, capabilities, and skills

• Bachelor’s degree in Data Science, Mathematics, Statistics, Econometrics, Computer Science, or a related field, plus 3+ years of applied data science experience.
• Experience with TCP/IP networking, cybersecurity technologies, and security-related telemetry.
• Experience monitoring models in production and identifying data quality, drift, or performance issues.
• Experience deploying statistical or machine learning models in production environments, including AWS SageMaker.
• Working knowledge of Large Language Models, natural language models, vector embeddings, and responsible AI practices such as fairness, reliability, and safety.