In this role you will develop mathematical models and analysis of findings regarding large-scale biometric technologies that are considered by DHS to reengineer how travelers are identified/verified at our borders. As these technologies are tested, this person will collect and analyze the raw data (to include ROC curves, FAR/FRR rates, and failure-to-acquire), perform predictive modeling, and brief decision-makers regarding the viability of the technology.
Develop an understanding of the customer’s data environment through data profiling and statistical analyses
Execute complex SQL queries of large Oracle table(s) efficiently. (Note: Advanced command of SQL is important – beyond just simple PROC SQL commands in SAS to include perhaps something like Toad or Oracle SQL Developer.)
Obtain, scrub, explore, model and interpret data currently stored in Oracle databases – using SQL and other data mining tools
Provide accuracy and biometric sample quality based on machine learning and statistical analyses
Mandatory Qualifications (Education, Certifications, Experience, Skills)
Bachelor's Degree in statistics or mathematics and minimum 10 years of experience or equivalent in the following:
Developing predictive models on accuracy using large data sets for high transactional volume environment
Evaluating and measuring performance of models
Common statistical modeling and techniques (e.g., linear regression, logistic regression, decision trees, etc.)
Understanding of and/or prior experience related to calculating False Acceptance Rate (FAR)/False Match Rate (FMR), False Rejection Rate (FRR)/False No-Match Rate (FNMR), True Acceptance Rate (TAR), and False Alarm Rate
Conceptual understanding of and/or prior experience related to data profiling, fuzzy matching, entity resolution, and signal detection theory (specifically with respect to SD theory: designing and improving upon systems that monitor, minimize, and balance false positive and false negative outcomes)
Experience related to biometric performance using Receiver Operating Characteristic (ROC), Detection Error Tradeoff (DET), Cumulative Match Characteristic (CMC) curves, and Identification and Detection Rate curves
Proficient in at least one of the following programming languages:
Experience with scripting languages for preprocessing and statistcal analysis (e.g. Python + Panda)
Proficient in at least one query language (e.g. SQL or HQL)
Desired Qualifications (Education, Certifications, Experience, Skills)
Understanding of big data ecoystems (e.g. Hadoop or Spark)
Salient CRGT is a leading provider of health, data analytics, cloud, agile software development, mobility, cyber security, and infrastructure solutions. We support these core capabilities with full lifecycle IT services and training—to help our customers meet critical goals for pivotal missions. We are purpose-built for IT transformation supporting federal civilian, defense, homeland, and intelligence agencies, as well as Fortune 1000 companies.
If you feel you are qualified for this position, express interest by clicking the Apply button below (if you are viewing this position on the Salient CRGT website). If you are viewing this job posting outside of the Salient CRGT website, please visit: www.salientcrgt.com/careers to express interest in this position through the Salient CRGT Careers page.
Salient CRGT is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, national origin, age, sex, sexual orientation, gender identity or expression, veteran status, disability, genetic information, or any other factor prohibited by applicable anti-discrimination laws.