Apply on Employer Site

CACI International Inc · 4 months ago

Product Architect (Data Scientist)

Sterling, VA

Full-time

Hybrid

Senior Level, Lead/Staff

$121K/yr - $266K/yr

10+ years exp

CACI International Inc is seeking a motivated Data Scientist and Product Architect with Agile methodology experience to join their Customs and Border Protection team in Northern Virginia. The role involves managing and utilizing data to design predictive maintenance models, conducting root cause analysis, and supporting IoT device signal analytics for the Integrated Traveler Initiative.

Information TechnologyService IndustrySoftware

Comp. & Benefits

No H1B

Security Clearance Required

U.S. Citizen Only

Responsibilities

Develop an understanding of the customer’s data environment through data profiling and statistical analyses

Execute complex SQL queries

Design and development of complex large scale OLTP systems

Obtain, scrub, explore, model and interpret data currently stored in Oracle various types of databases - using SQL and other data mining tools

Perform statistical analysis and tune using test results

Study appropriate datasets and transform data science prototypes

Research and implement appropriate machine learning algorithms and tools and develop machine learning applications according to requirements

Train data-driven learning model

Maintain and work with data pipeline that transfers and processes large scale of heterogenous structural/non-structural data using Spark, Scala, Python, Apache Kafka, TensorFlow, PyTorch, and/or other data analytic tools

Design, build and support pipelines of data transformation, conversion, validation

Build data manipulation, processing, and data visualization tools and share these tools across the team

Leverage the statistical and computational knowledge to build algorithms for reporting

Apply data analysis, data mining and data engineering to present data clearly and develop experiments

Ensure high-quality data and understand how data is generated out experimental design and how these experiments can produce actionable, trustworthy conclusions

Assist senior management in making key business decisions

Work with development teams to build tools for data logging and repeatable data tasks that will accelerate and automate data scientist duties

Qualification

Data ScienceMachine LearningSQLBig Data AnalyticsStatistical AnalysisPythonSparkData EngineeringAgile MethodologyProblem SolvingTeam LeadershipTime Management

Required

Must be a U.S. Citizen with the ability to pass CBP background investigation, criteria includes, but not limited to: 3-year check for felony convictions, 1-year check for illegal drug use, 1-year check for misconduct such as theft or fraud

Bachelor's degree in computer science, Math, Physics, Engineering, Statistics or other technical field and minimum 10 years of experience or equivalent

Conceptual understanding of – and/or prior experiences 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 manipulating large data sets through statistical software using SAS, SPSS, R, or Matlab or other methods

Experience with developing predictive models for using large data sets for high transactional volume environment

Experience with evaluating and measuring performance of models

Should have a firm understanding of common statistical modeling and techniques (e.g., linear regression, decision trees)

Strong algorithmic problem-solving skills

Experience with statistics, modeling and machine learning techniques Statistics including but limited to hypothesis testing, regression, clustering, classification, and optimization

Ability to understand and analyze data models – how the data is stored in relational databases

Ability to understand system integration aspects of integrating model input and output in transactional systems to help real time decision making

Good understanding software application architecture and develop integration approaches for predictive models

Possess the ability to perform with little direct supervision as a self-starter

Be a self-motivated, creative, and inquisitive problem solver with a strong work ethic and data integrity

Strong organization and time management skills – prior experience in leading a small team is preferred

Must be available to work a hybrid schedule with an on-site requirement in Sterling, VA

Preferred

Strong government/CBP platform experience

Experience working with Hadoop, Pig/Hive, Spark, MapReduce

Comprehensive Deep Learning and machine learning experience

Know Python and essential data analytical packages, PyTorch or TensorFlow

Bayesian learning and modeling experience

Knowledge of Probabilistic learning, time series analysis

Strong problem-solving skill and research capabilities

Computer vision and image processing background

Working knowledge of the CBP Port of Entry systems and/or their operational requirements

Experience automating business processes using RPA technologies

Benefits

Healthcare

Wellness

Financial

Retirement

Family support

Continuing education

Time off benefits

Company

CACI International Inc

Glassdoor4.0

At CACI International Inc (NYSE: CACI), our 25,000 talented and dynamic employees are ever vigilant in delivering distinctive expertise and technology to meet our customers’ greatest challenges in national security.

Founded in 1962

Arlington, Virginia, USA

10001+ employees