Citigroup Machine Learning and Data Science Lead Developer - Assistant Vice President - Irving, TX – (C12 R2196402) in Irving, Texas
Job Description: Citi Internal Audit Innovation technology team is seeking a highly motivated and strong hands-on Machine Learning and Data Science Lead Developer to expand the existing global team. The team is responsible for developing an integrated suite of innovative analytic solutions and services as part of the Audit Analytics platform. The platform serves the global Internal Audit organization and leverages cutting edge technologies in the areas of web-based data visualization and analytic processing using machine learning, big data and high performance distributed processing to empower auditors with greater interrogation and detection capabilities for various businesses and processes to provide data-driven insights.
The successful candidate should have proven machine learning and data science focused development experience, strong analytical skills, technical depth, and excellent written and verbal communication skills. Primary focus would be to lead development and integration of cognitive analytic solutions on the firm-wide risk and controls platform for Citi Internal Audit leveraging data sourced from Citi systems.
Key Responsibilities :
Lead cognitive solution development for a suite of applications within firm-wide risk & control platform in a globally distributed team.
Understand business challenges and formulate solutions using machine learning models for improving risk assurance and control effectiveness for internal audit.
Understand firm-wide data and apply techniques for feature engineering and selection
Apply state-of-the-art machine learning techniques to firm-wide data, including model selection, data anomaly detection, training, testing and validation
Lead end-to-end development of ML based solutions (including data retrieval, analysis, ML model development) to maintain the highest data quality and implementation in production systems
Analyze ML algorithms that could be used to solve a given problem and ranking them by their success probability
Explore and Visualize data to gain an understanding of it, then identifying differences in data distribution that could affect performance when deploying the model in the real world
Contribute to formulation of strategies for applications development and other functional areas
Verify data quality, and/or ensuring it via data cleaning
Supervise the data acquisition process if more data is needed
Find available datasets that could be used for training
Define validation strategies
Define the preprocessing or feature engineering to be done on a given dataset
Store preprocessed data for quick lookup when applicable
Define and develop data augmentation pipelines
Train models and tune their hyper-parameters
Understand requirements and code and unit test required components
Support acceptance tests and production test
Report progress on work and work collaboratively with the existing global team
Keep abreast of latest technological happenings in his work area and bring relevant ideas/concept to the table
Skills & Qualifications :
Background in Mathematics/ Economics/ Computer Science / Statistics or equivalent. Experience in finance is a strong advantage
6-8 years of relevant experience in Machine Learning/Data Scienc e field in the Financial Service industry
Basic knowledge of industry practices and standards
Knowledge of a variety of machine learning techniques (exploratory data analysis, predictive modelling, supervised/unsupervised machine learning, anomaly detection) and their real-world applications
Highly proficient in programming with Python libraries for machine learning ( scikit, pandas, spark-MLlib )
Proficiency with a deep learning framework such as TensorFlow or Keras
Experience with data visualization techniques. Integration with web applications and BI tools such as MicroStrategy, Arcadia or Tableau a plus
Proficiency in using query languages, such as SQL, Spark DataFrame API, etc.
Experience with Deep Learning, particularly when applied to financial data – an advantage.
Hands-on skills with Java a plus
Proficiency with OpenCV & PDFMiner a nice to have.
Self-motivated and team player that has the drive to learn and master new technologies and techniques.
Excellent communication skills and ability to explain your work in layman’s terms
Bachelor’s degree/University degree or equivalent experience
Master’s degree preferred
Job Family Group:
Citi is an equal opportunity and affirmative action employer.
Qualified applicants will receive consideration without regard to their race, color, religion, sex, sexual orientation, gender identity, national origin, disability, or status as a protected veteran.
Citigroup Inc. and its subsidiaries ("Citi”) invite all qualified interested applicants to apply for career opportunities. If you are a person with a disability and need a reasonable accommodation to use our search tools and/or apply for a career opportunity review Accessibility at Citi (https://www.citigroup.com/citi/accessibility/application-accessibility.htm) .
View the "EEO is the Law (https://www.dol.gov/sites/dolgov/files/ofccp/regs/compliance/posters/pdf/eeopost.pdf) " poster. View the EEO is the Law Supplement (https://www.dol.gov/sites/dolgov/files/ofccp/regs/compliance/posters/pdf/OFCCP_EEO_Supplement_Final_JRF_QA_508c.pdf) .
View the EEO Policy Statement (http://citi.com/citi/diversity/assets/pdf/eeo_aa_policy.pdf) .
View the Pay Transparency Posting (https://www.dol.gov/sites/dolgov/files/ofccp/pdf/pay-transp_%20English_formattedESQA508c.pdf)
Citi is an equal opportunity and affirmative action employer. Minority/Female/Veteran/Individuals with Disabilities/Sexual Orientation/Gender Identity.