• Sr. Data Scientist

    Job Locations US-Bethesda
    Posted Date 4 months ago(11/7/2018 12:50 PM)
    Job ID
  • Overview

    At Fidelis Cybersecurity, we are working at the confluence of two exciting fields in the world of high tech: Cyber Security and Data Science. The Fidelis Elevate platform collects deep visibility data from multiple vantage points—network, endpoint, and sandbox based malware execution, and combines it with high quality threat intelligence from our Threat Research team to detect advanced cyber threats.


    Our Data Science team, in close collaboration with software developers and threat researchers, is building the next generation of Machine Learning based features for the Fidelis Elevate platform. You will be a leading contributor on our team located in Bethesda, MD.


    Fidelis Cybersecurity is a fast-growing company that provides organizations with a robust, comprehensive portfolio of products, services, and expertise to combat today's sophisticated advanced threats and prevents data breaches. Our commercial enterprise and government customers around the globe can face advanced threats with confidence within our Network Defense and Forensics Services, delivered by an elite team of security professionals with decades of hands-on experience, and our award-winning Advanced Threat Defense Products, which provide visibility and control over the entire threat lifecycle


    Come join our awesome Engineering Team in the Bethesda, MD office!



    • Exploratory Data Analysis using Python and Big Data frameworks (Hadoop and Spark) to derive insights from our rich datasets.
    • Build machine learning models to detect malware and malicious network activity.
    • Consult with the development teams to drive the implementation of predictive models in our product.
    • Stay up-to-date with cutting edge research and development in machine learning, particularly as it applies to cybersecurity.
    • Work well in small team environment as individual contributor, team player, and broader organizational member


    Required Skills:   

    • Professional working experience in the range of 2-4 years in Data Science or the use of various quantitative, statistical, inference based techniques that require the interoperability of algorithms with key data labels to support certain operational, mission, or business areas
    • BS or MS (preferred) in Computer Science, Statistics, Mathematics with a GPA greater than 3.2 or other related fields.
    • Feature engineering experience to support model optimization, tuning, development, and/or implementation
    • Excellent understanding of the use, performance, trade-offs, benefits, pros-cons of various machine learning algorithms to include, but not be limited to, Random Forests, Logistic Regression, k-NN, Naïve Bayes, etc.
    • Demonstrated experience with prototyping, testing, and implementing Data Science based features for customer facing products.
    • Experience with Python based Data Science toolkits such as scikit-learn, scipy, numpy, and pandas.
    • Good applied statistical skills such as hypothesis testing as well as deep understanding of viable statistical inferencing techniques.
    • Excellent written, verbal, and oral communication skills in small groups to support technical communications
    • Ability to collaborate on research endeavors to include digesting current research activities and collaborating on proofs of concept (POC) and minimal viable products (MVP)
    • Experience doing data science through an Agile – Scrum – Kanban development process


    Bonus Skills:

    • Excellent understanding of the use, performance, trade-offs, benefits, pros-cons of various artificial neural network approaches to include but not be limited to multi-layer perceptron (MLP), natural language processing (NLP)
    • Experience with programming in Python or Scala for Apache Spark.
    • Experience with Apache Hadoop.
    • Knowledge of network protocols and network security.
    • Statistical modeling using R or Python.


    Sorry the Share function is not working properly at this moment. Please refresh the page and try again later.
    Share on your newsfeed