remote
AI Research Engineer - Representation Learning - Equifax
Research Engineer
Lead the design and deployment of Transformer‑based models for structured and time‑series credit risk data, focusing on representation learning and interpretable AI to drive robust risk assessment solutions.
About the role
Key Responsibilities
- Design, prototype, and production‑grade Transformer architectures tailored to structured and time‑series credit risk datasets.
- Develop and refine representation learning techniques that capture nuanced financial behaviors while ensuring model interpretability.
- Collaborate with data scientists and domain experts to integrate domain knowledge into model training and evaluation pipelines.
- Implement rigorous validation, bias detection, and explainability frameworks to meet regulatory and business standards.
- Document research findings, model specifications, and performance metrics for internal and external stakeholders.
Requirements
- Advanced degree (PhD or Master’s) in Computer Science, Statistics, or related field with a focus on machine learning.
- Proven experience building Transformer‑based models in Python using PyTorch or TensorFlow.
- Strong background in representation learning, time‑series analysis, and model interpretability.
- Familiarity with credit risk modeling and regulatory considerations is highly desirable.
- Excellent communication skills and ability to translate complex technical concepts to non‑technical audiences.