Назад
Company hidden
3 дня назад

Director, Credit Risk Management (Machine Learning)

200 000$
Формат работы
hybrid
Тип работы
fulltime
Грейд
director
Английский
b2
Страна
US
Вакансия из списка Hirify.GlobalВакансия из Hirify Global, списка международных tech-компаний
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/
TL;DR
Director, Credit Risk Management (Machine Learning): Owning credit policy, underwriting strategy, consumer credit model development, and portfolio surveillance with an accent on tree-based machine learning, scorecards, risk-based pricing, and regulated model governance. Focus on building and deploying production credit models, monitoring portfolio and model performance, and ensuring compliance with fair lending and model risk requirements.

Location: Draper, Utah, United States; hybrid, with in-office presence three days per week. Candidates must be located in Draper, Utah.

Annual compensation: $200,000, depending on experience.

Company

hirify.global is a diversified services company operating across student lending, consumer lending, payments processing, renewable energy, and K–12 and higher education.

What you will do

  • Own credit policy and underwriting strategy, including credit-box design, debt-to-income standards, loan terms, and risk-based pricing.
  • Perform segmentation, swap-set analysis, challenger testing, and profitability analysis to support credit expansion and model changes.
  • Build, validate, deploy, and integrate application, behavioral, account-management, PD/LGD, loss-forecasting, and collections-propensity models.
  • Monitor portfolio performance through vintage curves, roll rates, KRIs, model stability, calibration, and expected-versus-actual analysis.
  • Own model documentation, validation responses, remediation, inventory, and governance within a three-lines-of-defense framework.
  • Partner with Product, Data, Technology, Finance, Servicing, Collections, Risk, and Compliance, and present to senior stakeholders, auditors, regulators, and examiners.

Requirements

  • 8+ years of experience in consumer lending, preferably at a bank or regulated depository institution.
  • Demonstrated experience building credit models end to end and explaining their data, methodology, validation, and production performance.
  • Deep hands-on machine learning and statistical modeling experience, including tree-based segmentation and classical scorecards.
  • Proficiency with SQL and Python, including pandas, scikit-learn, and XGBoost or LightGBM; experience with R or SAS is also relevant.
  • Experience with large loan-level and credit-bureau datasets, reproducible workflows, formal risk governance, model risk management, audit, and regulatory examinations.
  • Must already be authorized to work in the United States without current or future visa sponsorship. Bachelor’s degree in a quantitative discipline required; advanced degree preferred.

Nice to have

  • Production machine learning experience with model explainability and fair-lending techniques, including SHAP, monotonic constraints, reason codes, and disparate-impact testing.
  • Experience with CECL, stress testing, capital planning, MLOps, model registries, automated scoring, drift monitoring, or multiple consumer asset classes.
  • FDIC, OCC, or state examination exposure, or experience in a growth-stage or de novo bank environment.

Culture & Benefits

  • Hybrid work arrangement supporting remote work for part of the week while maintaining regular in-office collaboration.
  • Medical, dental, vision, HSA, and FSA benefits.
  • Paid time off, 401(k), student loan repayment, life and disability insurance, and an employee assistance program.
  • Employee stock purchase program, tuition reimbursement, performance-based incentive pay, and wellness support.
  • Welcoming and respectful workplace with equal employment opportunity and reasonable accommodation support.

Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →