Risk Analytics Associate - Synthetic Data

At Verisk CRS (Catastrophe and Risk Solutions), we do some cutting edge and advanced analytic stuff!  We build stochastic models to simulate Catastrophic Events that will inform the insurance industry.  Events include Hurricanes, Earthquakes, and Flooding, just to name a few.  We then run Monte Carlo simulations to provide hundreds of thousands of years of simulated events. These help the insurance industry make objective and data driven decisions based on their risk tolerances.  As a company, we have a strong sense of purpose and know we are helping communities worldwide become more resilient.
We’re expanding our capabilities to create synthetic client data using AI, and we’re looking for a mid-level analyst to join this exciting new initiative.

Responsibilities
As a Risk Analytics Associate, you will play a key role in profiling client data, collecting workflow observability metrics, and using these insights to train and deploy models that generate synthetic client data tailored for insurance and catastrophe modeling. This will be done by leveraging various data analysis methods including 3rd party AI tools, with the intent that you become a Data Analytics & AI Subject Matter Expert for the Model Validation Team.
We hire intellectually curious people - if you understand the descriptions above then we are interested in engaging with you.

•    Collaborate with 3rd party vendors to communicate business requirements for building, training, and implementing AI model for synthetic data generation. 
•    Deploy above AI models along with other data analytics tools to profile client data, ensuring a deep understanding of data composition while maintaining strict data security and privacy standards.
•    Collect, process, and analyze workflow observability metrics from production systems for business informed test design.
•    Collaborate with sales, client services, and business stakeholders to define requirements and deliver solutions that meet client and regulatory needs.
•    Document processes, findings, and best practices for future team reference.
•    Communicate results and recommendations clearly to technical and non-technical audiences.

Qualifications
•    Bachelor’s degree in a STEM field (data science, engineering, mathematics, computer science, etc.).
•    2–4 years of experience in data analysis, data engineering, or related roles.
•    Experience with Python, SQL, and data manipulation libraries (Pandas, Tidyverse, etc.).
•    Familiarity with Generative AI tools for use in code development (Claude, GitHub Co-Pilot, Cursor, etc.)
•    Experience working with large datasets and data visualization tools.
•    Strong attention to detail and analytical mindset.
•    Excellent communication and teamwork skills, with a proactive & innovative approach.
•    Willingness to learn new technologies and approaches as the project evolves.
Preferred Qualifications
•    Exposure to cloud platforms (AWS, Azure) and version control (GitHub).
•    Experience with synthetic data frameworks (SDV, YData SDK, Faker, etc.) is a plus.
•    Understanding of data privacy, security, and ethical AI principles.