Data Scientist

Bank of America•Plano, TX

5d•Onsite

About The Position

Bank of America’s Client Protection Technology (CPT) organization, focused on authentication technology for customer-facing applications, is seeking a Machine Learning Engineer or Data Scientist to deliver complex classification models from data exploration through production implementation. The role analyzes and interprets large datasets to identify business insights, support revenue generation, and develop risk-management strategies. It involves working directly with large datasets, developing repeatable data pipelines, writing maintainable code, troubleshooting data and model issues, documenting technical decisions, and partnering with engineering teams to integrate models into scalable production workflows. The successful candidate will build, train, validate, and tune supervised classification models using structured, behavioral, and transactional data. They will develop Python-based workflows for data preparation, model training, evaluation, and scoring, and support real-time or near-real-time inference in production decisioning workflows. The role also includes communicating findings and technical recommendations to stakeholders, maintaining documentation, managing multiple priorities, applying agile practices, mitigating risk, and researching advances in data science and artificial intelligence. Bank of America describes its culture as focused on Responsible Growth, inclusion, collaboration, career development, and teammate wellness. The company has an in-office culture with role-specific flexibility based on responsibilities and business needs. This position is 1st shift and is listed as 40 hours per week.

Requirements

Master’s or PhD in a quantitative or technical field such as computer science, statistics, mathematics, engineering, data science, or a related discipline.
At least 5 years of hands-on data science or machine-learning engineering experience delivering models, pipelines, or analytics solutions in highly technical environments.
Strong Python development experience and experience with data science and machine-learning libraries such as pandas, NumPy, scikit-learn, XGBoost, or similar frameworks.
Deep understanding of supervised machine-learning classification, including feature engineering, model training, hyperparameter tuning, validation, threshold selection, and performance evaluation.
Experience working with large structured datasets, including cleansing, transformation, exploratory analysis, and repeatable data-preparation workflows.
Ability to evaluate classification models using precision, recall, F1 score, ROC-AUC, confusion matrices, and false-positive or false-negative analysis.
Experience packaging, versioning, testing, and integrating machine-learning models or scoring logic into production or near-production application workflows.
Strong technical communication and documentation skills, including explaining model assumptions, feature logic, validation results, implementation details, and operational tradeoffs.
Experience designing, deploying, or supporting machine-learning models requiring real-time or near-real-time inference, including low-latency scoring, performance optimization, and production decisioning integration.
Understanding of explainable AI, model governance, responsible AI practices, bias evaluation, auditability, and risk controls for production machine-learning systems.
Experience using GenAI tools such as Copilot to create agents and develop effective prompts supporting daily tasks.
Skills include adaptability, attention to detail, business analytics, technical documentation, written communications, agile practices, application development, collaboration, data visualization, DevOps practices, artificial intelligence and machine learning, networking, policies and procedures, presentation skills, and risk management.

Nice To Haves

Experience developing classification models for fraud, risk, cybersecurity, authentication, customer behavior, anomaly detection, or other high-volume decisioning use cases.
Familiarity with MLOps practices, including model packaging, version control, automated testing, CI/CD pipelines, model monitoring, and reproducible deployment workflows.
Experience with distributed data processing, cloud platforms, or large-scale analytics environments such as Spark, Databricks, Hadoop, AWS, Azure, or similar technologies.

Responsibilities

Perform business analytics, including data analysis, trend identification, and pattern recognition, using techniques such as machine learning, text mining, and statistical analysis.
Apply agile practices to project management, solution development, deployment, and maintenance.
Create and maintain technical documentation covering business requirements, analytical solution specifications, and production implementation.
Manage multiple priorities and deliver quality work on time, including quantitative models, data science products, analysis reports, and visualizations; work independently and as part of a team.
Present technical concepts and analysis results to diverse internal stakeholders in person and virtually, and build professional relationships that support collaboration.
Identify potential issues and develop controls to mitigate risk.
Research advances in data science and artificial intelligence to support business analytics.
Design, build, train, validate, and tune supervised machine-learning classification models using structured, behavioral, and transactional data.
Explore, cleanse, and transform data, and engineer features to create reliable model inputs.
Develop repeatable Python workflows, scripts, and pipelines for dataset preparation, model training, evaluation, and scoring.
Package, version, test, and integrate machine-learning models or scoring logic into production or near-production workflows.
Support real-time or near-real-time model inference, including low-latency scoring, performance optimization, and integration with production decisioning workflows.