Cyber Data Scientist - Boston, United States - State Street

State Street

Verified Company

Boston, United States

3 weeks ago

Posted by:

Mark Lane

beBee recruiter

Description

Who we are looking for

The State Street Security Architecture, Analytics & Fusion Engineering (SA_2_FE) team is looking for a Cybersecurity Modeling Scientist.

The Fusion Analytics and Data Engineering team delivers models and insights to help Cybersecurity teams make faster, more informed decisions as we work to secure State Street's digital footprint.

As a Modeling Scientist, you will develop the data flows, analytics pipelines, and production machine-learning systems - in collaboration with data product managers, architects, engineers, and other team members - to create analytics & ML-driven data products that support our mission to build predictive models and intelligent systems that help secure State Street's information and infrastructure.

Due to the role requirements this job needs to be performed primarily in the office with some flex work opportunities available.

What you will be responsible for

As Cybersecurity Modeling Scientist you will

Work hand in hand with product owners and domain experts from across the Global Cybersecurity organization to develop novel analytics and ML solutions for critical identity, security, and risk management problems.
Analyze large datasets using SQL and scripting languages to surface meaningful/actionable insights and opportunities to partner teams and other key stakeholders
Approach problems from first principles, using a variety of statistical and mathematical modeling techniques to research and understand behaviors and interactions
Work with data analytics engineers to log new, useful data sources as we expand our portfolio of security tools and platforms, and with data platform engineers to develop capabilities for data and model operationalization
Build, forecast, and report on metrics that drive strategy and facilitate decision making for key security initiatives
Build, manage, deploy, and monitor endtoend analytical and machinelearning solutions to scale our cyber behavioral intelligence platform
Build and share data visualizations and selfserve dashboards for your product team, and support planning, facilitation, and execution of regular communication and coordination across crossfunctional teams

What we value

These skills will help you succeed in this role

PhD in a quantitative technical field with 2+ years of relevant industry experience OR Bachelor's degree in a quantitative field with a minimum of 5 years of industry experience.
Direct relevant experience building ML models and analytics for cybersecurity, insurance, and other data intensive risk management related domains, structuring large volumes of operational and log data in cloud native analytics environments.
Demonstrated ability to work as an independent contributor driving research and analyses from conception to implementation with mínimal guidance.
Experience with scripting and data analysis programming languages, such as Python or R and advanced proficiency with SQL and data visualization tools
Familiarity with the modern data science tools such as Pandas, Scikit-Learn, XGBoost, TensorFlow/Keras, MLFlow, Jupyter Notebooks
Experience with cohort and funnel analyses, population clustering and segmentation techniques, and a deep understanding statistical concepts related to experimental design, selection bias, probability distributions, and Bayesian inference
Experience answering unstructured questions, driving datadriven solutions, and managing projects and tasks to a conclusion

Education & Preferred Qualifications

Direct experience in the cybersecurity industry building analytics, models and detections (minimum 12 years).
Familiarity with statistical and ML models for graph analysis, risk modeling in the actuarial or financial domain.
Deep understanding of tools and techniques for fraud modeling and anomaly detection, forecasting and timeseries analysis, and adaptive and reinforcement learning techniques.
Experience using batch and realtime feature stores, and developing coordinated batch, streaming and online model execution workflows.
Experience with data ops and big data tools such as Spark, Spark Streaming, Presto/Trino, Kafka,, Snowflake within cloud environments such as AWS, GCP, and Azure.
Experience with MLOps and iterative cycles of endtoend development, MRM coordination, deployment and monitoring of production grade ML models in a regulated highgrowth tech environment

We truly believe in the power that comes from the diverse backgrounds and experiences our employees bring with them.

Although each vacancy details what we are looking for, we don't necessarily need you to fulfil all of them when applying.

If you like change and innovation, seek to see the bigger picture, make data driven decisions and are a good team player, you could be a great fit.

Why this role is important to us

Our technology function, Global Technology Services (GTS), is vital to State Street and is the key enabler for our business to deliver d