Legion Systems is seeking a Senior Data Scientist supporting Multi-Domain Task Force – Pacific (MDTF-Pacific).  Provides a team of highly skilled engineers and data scientists to collect, ingest, process, analyze, visualize, and share data in support the United States Indo-Pacific Command (USINDOPACOM).  The team will be responsible for the assembly of infrastructure within a cloud environment that is scalable, highly available, and adaptable with multiple environments that take advantage of managed services in the cloud.

Involved in the analysis of unstructured and semi-structured data, including latent semantic indexing (LSI), entity identification and tagging, complex event processing (CEP), and the application of analysis algorithms on distributed, clustered, and cloud-based high-performance infrastructures. Exercises creativity in applying non-traditional approaches to large-scale analysis of unstructured data in support of high-value use cases visualized through multi-dimensional interfaces. Handle processing and index requests against high-volume collections of data and high-velocity data streams. Has the ability to make discoveries in the world of big data. Requires strong technical and computational skills – engineering, physics, mathematics, coupled with the ability to code design, develop, and deploy sophisticated applications using advanced unstructured and semi-structured data analysis techniques and utilizing high-performance computing environments. Has the ability to utilize advanced tools and computational skills to interpret, connect, predict and make discoveries in complex data and deliver recommendations for business and analytic decisions. Experience with software development, either an open-source enterprise software development stack (Java/Linux/Ruby/Python) or a Windows development stack (.NET, C#, C++). Experience with data transport and transformation APIs and technologies such as JSON, XML, XSLT, JDBC, SOAP and REST. Experience with Cloud-based data analysis tools including Hadoop and Mahout, Acumulo, Hive, Impala, Pig, and similar. Experience with visual analytic tools like Microsoft Pivot, Palantir, or Visual Analytics. Experience with open-source textual processing such as Lucene, Sphinx, Nutch or Solr. Experience with entity extraction and conceptual search technologies such as LSI, LDA, etc. Experience with machine learning, algorithm analysis, and data clustering.


BS 12-15, MS 10-13. PhD 10+

Requires the following skillsets:
Capable of building Python scripts and packages that will be used by the data analysts. The Python scripts will use supervised and unsupervised ML (both text and image-based machine learning), natural language processing (named entity extraction, summarization, etc.), and network analysis (social network analysis, centrality analysis, dynamic network analysis).

- Must have expertise in maintaining and deploying a notebook-based data science environment (JupyterHub).

-Must have experience in advanced Python data science packages (pandas, networkx, scikit-learn, pyTorch or TensorFlow/Keras, matplotlib or plotly, etc.)

-Work location is Joint Base Lewis Mcchord with the Multi-Domain Task Force.

Clearance Required: Must hold an active TS/SCI clearance.

Required Certification:

Must hold the appropriate DoD 8570.01 baseline certification applicable to their work role prior to beginning work.

Work schedule is Monday-Friday, from 8 am – 5 pm.