Risk AI Data Scientist

Details

ING Hubs Poland is hiring a Risk AI Data Scientist to drive the integration of advanced AI capabilities into the bank's overall risk management, including credit risk model maintenance. The role operates at the intersection of risk management, credit risk modelling, model lifecycle governance, and advanced AI technologies such as LLMs, NLP, and agentic workflows. The successful candidate will help design the cognitive layer of the bank's risk management environment and turn advanced AI into production-ready, compliant solutions.

Responsibilities

• Develop custom models by fine-tuning open-weight models such as Llama and Mistral on GCP GPUs for wholesale and retail banking, credit policies, and financial risk use cases.
• Explore, productionise, and scale AI models.
• Evaluate and monitor generative AI systems, including hallucinations, quality, and model drift.
• Architect Retrieval-Augmented Generation (RAG) systems for interacting with internal policy documents, regulations, and other documentation in different formats.
• Work with large-scale unstructured data, including documents, PDFs, and OCR outputs.
• Design and implement agentic AI workflows using technologies such as LangChain and LangGraph.
• Build NLP pipelines to extract complex signals, including transaction patterns and legal clauses, from unstructured text and convert them into usable features.
• Write clean, modular Python code in Azure DevOps.
• Ensure models are testable, reproducible, and ready for deployment.

Requirements

• Master's degree in mathematics, economics, or an equivalent field.
• At least 7 years of experience in risk management; experience with risk modelling is an advantage.
• Advanced Python and SQL skills.
• Experience with PyTorch or TensorFlow; SAS is an advantage.
• Experience with Hugging Face, including Transformers and PEFT.
• Experience with LangChain or LlamaIndex.
• Experience with vector stores such as FAISS or Vertex Search.
• Experience designing and optimising RAG pipelines.
• Experience manipulating and governing structured and unstructured data for risk management purposes.
• Experience with Google Cloud Platform, including Vertex AI and Workbench.
• Strong experience with Azure DevOps, Git, and Pipelines.
• Experience building end-to-end data, model, and deployment pipelines.
• Experience working in Agile/Scrum teams is an advantage.
• Knowledge of AI risk governance is an advantage.

Team Information

The Integrated Risk team provides risk identification, aggregation, and insight capabilities at Group level across various risk domains. The team supports risk governance, policies, frameworks, and group-wide model and implementation activities across locations.

The Bank-wide Credit Risk Models department manages Wholesale Banking IRB and IFRS9 models and Bank-wide Credit Risk Economic Capital models, including their development, monitoring, and advisory support. These group-wide models are managed and developed centrally and applied consistently across ING locations.

The global ING job architecture title for this role is Data Scientist IV.