Lead Data Scientist (model Developer) / Deep Learning Practitioner

Capital One Capital One · Banking · Nottingham, United Kingdom

Lead Data Scientist role focused on developing and deploying deep learning models for underwriting capabilities in a fintech company. The role involves advancing existing models, building neural networks, transforming multi-modal inputs, and driving projects from prototype to production. Requires experience in sequential data, model development leadership, and modern ML frameworks.

What you'd actually do

  1. Lead the development of next generation deep learning approaches to advance our current underwriting models, to ensure that our core lending capabilities remain at the forefront of the industry.
  2. Unlock the value in non-traditional datasets by building sophisticated neural networks (e.g. LSTMs, RNNs, or Transformers). You will find novel ways to transform raw, multi-modal inputs into powerful predictive features.
  3. Collaborate with business stakeholders to prioritize initiatives. You will bridge the gap between ambitious R&D and tangible in-market results, driving ideas from initial prototypes through to production.
  4. Use a combination of business acumen, coding and statistical skills to navigate large amounts of data and extract actionable solutions.
  5. Work cross-functionally on projects that support key business initiatives and drive sustainable growth.

Skills

Required

  • Strong experience developing and deploying deep learning models, particularly for sequential data (e.g. time series or language models).
  • A proven track record leading model development, including setting the technical direction, project management, stakeholder comms, and mentoring junior members of the team.
  • Experience producing and managing reliable and maintainable code in SQL/Python in a team setting, including code reviews and setting software engineering best practices
  • Hands-on experience with modern Machine/Deep Learning frameworks such as PyTorch, TensorFlow, or Hugging Face Transformers, including training deep learning models on GPUs or GPU clusters.
  • Experience working with structured and unstructured data, such as text, logs, or time series and tokenisation techniques.
  • A strong understanding of probability, statistics, machine learning and familiarity with large data set manipulation.

Nice to have

  • A drive for continued learning through an internal and external focus, and an ability to prototype new techniques to assess value

What the JD emphasized

  • lead the development
  • leading model development
  • deep learning models
  • neural networks

Other signals

  • lead the development of next generation deep learning approaches
  • advance our current underwriting models
  • improve predictive power
  • generate high-impact customer insights
  • building sophisticated neural networks
  • transform raw, multi-modal inputs into powerful predictive features
  • driving ideas from initial prototypes through to production
  • developing and deploying deep learning models
  • leading model development
  • training deep learning models on GPUs or GPU clusters