Sr. Data Scientist

SMX is seeking a Sr. Data Scientist to provide analysis of unstructured and structure data sets using data mining, statistical analysis, explanatory and predictive modeling, and other techniques.  As a Data Scientist you will leverage large-scale data to build insights focused on customer patterns by enabling business applications, providing data science insights, such as segmentation, pairing recommendations, and other perceptions derived from data.  

As part of a team, you will deploy data science capabilities using multiple technological and computational methodologies, to provide insight and understanding of the operational environment or point of interest.

Essential Duties and Responsibilities: 

• Support the definition and documentation of functional and performance requirements, modes of operation, technical performance measures, measures of effectiveness, design characteristics, and human factors requirements
• Use scientific methodologies to develop and test models for scalable predictive and prescriptive analytics solutions  Create innovative statistical models and technical approaches that address complex business issues
• Conduct exploratory data analysis and create compelling visualizations using complex and high-dimensional datasets
• Identify suitable machine learning or statistical approaches depending on type of problem and train models for optimal performance, including hyperparameter tuning
• Determine best practices and develop actionable insights and recommendations for the current operations or issues and works closely with the business functional teams to address and drive continuous improvement
• Validate and monitor models to ensure consistent performance and avoid performance degradation Deploy models into production with assistance from Product Engineers
• Lead technical and analytics capability building within the analytics team in order to stay current on best practices and new modeling techniques
• Responsible for generating and maximizing value from analytics solutions  Utilize data lakes to compile a useable and actionable format from multiple disparate sources
• Identify patterns and trends in datasets, design algorithms and data manipulation capabilities using Python and various libraries, and use machine learning techniques to improve the quality of data for the customer
• Work collaboratively with Intelligence and Data Analysis teams to produce qualitative and quantitative data that support intelligence products

Required Skills/Experience: 

• Clearance: TS/SCI Eligible
• Mon - Friday on site support in Charlottesville, VA
• Security+ Certification
• Expertise in analytics tools including R, Python, SAS, SPSS, or STATA (Data visualization experience is a big plus)
• Expertise in the analysis and interpretation of data including the understanding of mathematical and statistical concepts
• Proficiency in exploratory data analysis and interpreting data
• Expertise with statistical modeling, machine learning algorithms, and analytics techniques like Regression, Classification, Clustering, Dimensionality reduction
• Proficiency in AWS: Redshift, S3, SageMaker  Hands-on experience in Python and knowledge of SQL
• Expertise working with cloud technologies such as AWS, Kafka, Spark, Storm, or Hadoop
• Expertise with the following types of data science techniques: Forecasting, Recommendation Systems, Logistics Optimization, Churn Analysis, Segmentation Analysis, Deep Learning
• Bachelor’s degree in a quantitative field such as Statistics, Mathematics, Computer Science, Data Science, or a related Engineering degree required Advanced degree in Computer Science or other quantitative field preferred
• 10+ years of experience in analytics space 

#cjpost

#LI-onsite