Description

You will build predictive models, validate production model behavior, and ensure optimal performance across client environments.

Responsibilities

• Evaluate predictive and decision models by analyzing large historical datasets, performing data clean-up, and identifying patterns.
• Support model go-lives through production data validations and score distribution analysis for global clients.
• Conduct client meetings to communicate project status, discuss data quality, and resolve production data issues.
• Apply data mining methodologies to analyze model behavior and provide technical support for model construction and pre-sales.
• Manage limited-scope projects and collaborate with software, IT, and product teams to integrate analytics solutions.

Required Skills

• Experience with Python, Perl, C, C++, or Java.
• Proficiency in data cleaning, standardization, and normalization of large datasets.
• Ability to perform statistical analyses to understand dataset structures.
• Familiarity with basic software design principles and coding standards.
• Strong written and oral English communication skills for technical client interaction.
• Degree in Statistics, Engineering, Mathematics, Computer Science, Physics, or Operations Research.
• 5+ years of working experience.

Preferred Skills

• Experience with Hadoop, Spark, Hive, and Unix/Linux shell scripting.
• Knowledge of Bayesian networks, PCA, independent component analysis, linear/logistic regressions, neural networks, or SVM.
• Prior industry or academic experience in predictive modeling and data mining.

Key Skills

Education

Any Graduate