Data Scientist

Systems Planning and Analysis, Inc. (SPA) delivers high-impact, technical solutions to complex national security issues. With over 50 years of business expertise and consistent growth, we are known for continuous innovation for our government customers, in both the US and abroad. Our exceptionally talented team is highly collaborative in spirit and practice, producing Results that Matter. Come work with the best! We offer opportunity, unique challenges, and clear-sighted commitment to the mission. SPA: Objective. Responsive. Trusted.

The Joint, Office of the Secretary of Defense, Interagency Division (JOID) provides expert support services to a range of customers spanning across the Department of Defense, Federal Civilian, and international markets. JOID provides a diverse portfolio of analytical and programmatic capabilities to help our customers make informed decisions on their most challenging issues.

JOID assists the Defense Threat Reduction Agency (DTRA) in developing leading edge technologies to counter WMD in support of CCMDs and transitioning these technologies to military services and COCOMs. SPA provides expertise across the full range of chemical, biological, radiological, nuclear, and high-yield explosives (CBRNE) WMD, Counter Improvised Threat and Countering Threat Network technologies to support understanding, detection, identification, characterization, denial, control, disabling, defeating, disposing, safeguarding the force, managing consequences, and test and evaluation in support of military and civilian operations.

We have a near-term need for a Data Scientist to provide onsite support out of Lorton, VA.

The successful candidate will assist the Nuclear Technologies Detection (NTD) Division in providing a data science services capable of supporting scalable, highly available application solutions that leverage cloud native services; supporting the transformation of monolithic, legacy applications to a more modular, micro-services architecture; Providing artificial intelligence and machine learning (AI/ML) pipeline architecture design, development, and test knowledge and expertise with respect to AI/ML areas including natural language processing, computer vision, machine learning, and large language modeling; providing data architecture design, development and test knowledge and expertise with respect to cloud architecture, design patterns, and data analysis requirements; and defining data architectures that support both the enterprise and application-level capabilities with systems and network security, scalability, fault tolerance and optimal performance.

Support analysis and development of customer-driven technical data architectures and solutions. Provide technical guidance to AI/ML and data science development teams designing, developing, and integrating AI/ML pipelines and models. Provide technical guidance to software development teams designing, developing and integrating a data-intensive application framework using modern data-centric enabling technologies, cloud computing and virtualization architecture. Provide recommendations for technology implementations, application & data migration techniques and tools for the most efficient solution to meet mission needs, including present and future capacity requirements. Support the transformation of monolithic, legacy applications to a more modular, micro-services architecture. Analyze and recommend approaches for making heterogeneous data sources broadly available for discoverability and access to support a wide consumer-base, analytic needs, and use by diverse applications, services, and systems. Aid in optimizing the management of data across nodes and the performance of distribution, search and retrieval. Execute analytical experiments and prototyping to help solve problems across various domains and industries. Identify relevant data sources and sets to mine for client business needs, and collect large structured and unstructured datasets and variables. Research and evaluate new technology, review existing technology and architecture development patterns and practices, help guide and estimate new feature development, architectural and development guardrails, and identify ways to measure architecture maturity objectively, to include identifying performance bottlenecks and evaluating scaling benchmarks. Write and provide technical reports and white papers describing state-of-the-art technology and methodology research, evaluation, and recommendations.

15-30% travel required.

Required:

Master's degree in data science, computer science, or a related technical discipline with 1-3 years of experience OR a Bachelors with 5-7 years of experience.
• Proficiency with AI/ML pipeline design and development in enterprise solutions.
• Proficiency with and knowledge of development environments, frameworks (DevSecOps, MLOps), modern scripting language(s) (e.g., Python, SQL, R, etc.) or a programming language (e.g., Java, C++).
• Excellent understanding of machine learning techniques and algorithms, such as k-NN, Naive Bayes, SVM, and Decision Forests, as well as modern large-language models (LLAMA, BERT, GPT, etc.).
• Experience with DoD Risk Management Framework (RMF), AI RMF, and/or Enterprise Risk Management.
• Familiarity with designing and developing microservices ML architectures, and model and software containerization.
• Familiarity with program application interfaces (APIs) and cloud services (e.g., AWS, MS Azure).
• Familiarity with estimating software development resource requirements.
• Experience transitioning legacy systems to cloud environment optimized applications.
• Ability to provide recommendations derived from complex set of requirements.
• Must be able to work independently and complete tasking with minimum guidance and supervision in a dynamic, research-oriented group that has several concurrent projects.
• Strong working knowledge of Microsoft Office products and use of MS Teams, Workflows, and PowerBI.
• Active Secret clearance and the ability to attain and hold a TS clearance; SCI eligible.

Desired:

• Experience with federated machine learning and federated data processing and ingestion
• Professional certifications in related topics and tools (e.g., Elasticsearch engineer, database design, NVIDIA-Certified Associate)
• Experience in DoD Dev/Sec/Ops delivery of software capabilities
• Experience with DoD Command & Control (C2) networks (JADC2, IEW, etc.)
• Knowledge of the DoD Architecture Framework (DoDAF)
• Working knowledge of DTRA RD's mission and organization
• Active TS/SCI clearance