What are the responsibilities and job description for the Data Scientist position at SoTalent?
Company Overview
A U.S.financial services company with a global preecnece, best known for its credit card offerings, but also operating in consumer banking, auto lending, and commercial banking.
Job Overview
Join a fast-moving data science team focused on developing cutting-edge fraud detection systems for a major U.S. bank. Work with massive datasets and cutting-edge tools to solve real-world problems that directly impact millions of customers. Your mission: use advanced machine learning techniques to spot and prevent suspicious activity before it affects people’s money.
About the Team:
The fraud defense group is laser-focused on protecting personal banking accounts from takeover attempts and other fraudulent behavior. They are always iterating — combining deep technical knowledge with fresh ideas from research and industry to keep our models sharp.
They build features in Python, Spark, and SQL, and train models using modern Python ML libraries. Deployments happen across both batch and real-time systems, with data scientists often owning the process end-to-end or collaborating with engineering on more complex integrations.
What You’ll Do:
- Use Python, Spark, AWS, H2O, Kubernetes, and other modern tools to build deep learning models that identify fraud patterns in large-scale data
- Apply advanced sequence modeling (e.g., LSTMs, transformers, tabular embeddings) to uncover subtle signals in customer behavior
- Align model development with key anti-fraud initiatives in the business
- Lead projects from exploration to deployment, including experimentation, validation, and monitoring
- Collaborate closely with data engineers, analysts, product teams, and other data scientists
- Help define the research roadmap and identify opportunities to innovate
Who You Are:
- You bring originality to tough, ambiguous problems and enjoy pushing boundaries
- You’re technically solid, especially in Python and cloud-native ML tools
- You work confidently with structured and unstructured datasets and know your way around relational databases
- You take initiative and look for ways to improve processes, systems, and outcomes
- You care about developing talent and elevating your peers
Minimum Requirements:
- Bachelor’s degree and at least 6 years of experience in data analytics, or
- Master’s degree and at least 4 years of experience, or
- PhD and at least 1 year of experience (degree must be completed before start)
- At least 2 years of experience coding in open-source languages for large-scale analytics
- At least 2 years of experience with machine learning
- At least 2 years of experience with SQL or similar relational databases
Preferred Qualifications:
- PhD in a STEM discipline and 3 years of analytics experience
- 4 years working with Python at scale
- 4 years of experience with deep learning, especially for sequence modeling
- 1 year of hands-on experience with AWS
Salary : $175,000 - $200,000
