Quant Modeling Lead - Python in London

As a Python Developer within the Wholesale Credit Quantitative Research Core team, you will play a central role in building and maintaining Nova – the firm’s strategic platform for Loan Loss Forecasting models. Nova is built within JPMorgan’s Athena platform and underpins critical regulatory and business processes including CECL, IFRS 9, CCAR, ICAAP, and Risk Appetite forecasting.

You will be responsible for designing and implementing the core frameworks and libraries that model developers rely on to build, test, and deploy forecasting models at scale. This is a hands‑on engineering role that demands strong software craftsmanship, quantitative aptitude, and the ability to translate partially defined business needs into robust, production‑quality systems. You will work closely with quantitative researchers, model governance, technology partners, and wholesale credit business stakeholders.

Job Responsibilities

• Design, build, and maintain the core Python frameworks and libraries that power Nova, ensuring they are performant, extensible, and easy for model developers to integrate with.
• Develop and enhance the calculation engine and related tooling for loan loss forecasting models, supporting CECL, IFRS 9, CCAR, ICAAP, and Risk Appetite requirements.
• Implement high‑performance numerical algorithms using Python scientific computing libraries including NumPy, Pandas, and DuckDB.
• Champion test‑driven development practices across the team, building and maintaining comprehensive unit, integration, and regression test suites to ensure framework reliability.
• Take partially specified problems and business needs from stakeholders and translate them into concrete technical requirements, designs, and implementation plans.
• Leverage LLM‑based coding tools (e.g., GitHub Copilot, Claude) to accelerate development velocity, drive code quality, and maximize team productivity.
• Perform peer code reviews with a focus on correctness, performance, maintainability, and adherence to team standards.
• Prepare clear and thorough technical documentation covering design decisions, implementation details, and testing strategies.
• Partner with model developers, product and business stakeholders during the implementation, testing, and operationalization of forecasting processes.
• Present regular updates on development progress, technical decisions, and platform roadmap to senior management and cross‑functional stakeholders.
• Investigate and debug counter‑intuitive observations in model forecasts, performing root‑cause analysis at the framework and data level.

Required Qualifications, Capabilities, and Skills

• Bachelor’s or Master’s degree in Computer Science, Mathematics, Physics, Engineering, or a related quantitative discipline.
• Minimum 5 years of experience in quantitative software development within a financial services environment (e.g., banking, asset management, hedge fund, fintech).
• Advanced proficiency in Python with deep experience in object‑oriented design, design patterns, and building production‑grade frameworks and libraries.
• Strong working knowledge of NumPy and Pandas for numerical computing and data manipulation.
• Demonstrated experience with test‑driven development and building systems with rigorous unit, integration, and regression test coverage (e.g., pytest, unittest).
• Strong analytical, quantitative, and problem‑solving skills with the ability to reason about complex model behavior and data flows.
• Excellent written and verbal communication skills, with the confidence to present technical concepts to both technical and non‑technical audiences.
• Proven ability to operate as a self‑starter: taking ambiguous or partially specified problems and driving them through to well‑defined technical solutions.
• Proficiency with LLM‑based coding tools and a track record of leveraging AI assistants to meaningfully increase development productivity and code quality.

Preferred Qualifications, Capabilities, and Skills

• Experience with DuckDB or similar in‑process analytical databases for high‑performance data querying and transformation.
• Knowledge of credit risk concepts including Wholesale Credit, CCAR/DFAST stress testing, CECL/IFRS 9 allowance, and Basel III regulatory capital.
• Experience working with or building upon large‑scale analytics platforms (e.g., JPMorgan Athena or comparable quantitative computing environments).
• Familiarity with distributed computing frameworks and techniques for scaling numerical workloads.
• Knowledge of statistical modeling, Monte Carlo simulation, and time‑series forecasting methodologies.
• Ability to work effectively with large datasets and practical knowledge of SQL and database systems.
• Proven ability to build collaborative relationships with cross‑functional partners including model developers, business stakeholders, and technology teams.