Job Requirements
Merrifield, VA
Secret Polygraph not specified
Mid Level Career (5+ yrs experience)
Salary not specified
Join Premium to unlock estimated salaries 
Job Description
Data Scientist – NLP / Large Language Models (LLM)
Company: Complete Data Solutions (CDS)
Location: Merrifield, VA (On-Site)
Employment Type: Full-Time
Security Clearance: Active Secret Clearance Required
About Complete Data Solutions
Complete Data Solutions (CDS) is a leading data engineering and analytics company specializing in innovative solutions to complex data challenges for the federal government. For more than 25 years, CDS has proudly supported the Law Enforcement and Intelligence Communities, delivering advanced data engineering, analytics, system design and development, and reporting solutions.
At CDS, our employees are our greatest asset. We offer competitive salaries and a comprehensive benefits package, including health insurance, 401(k), competitive paid annual leave, tuition reimbursement, and additional benefits that reflect our long-term commitment to our employees' professional growth and well-being.
Position Overview
Complete Data Solutions is seeking an experienced Data Scientist specializing in Natural Language Processing (NLP) and Large Language Models (LLMs) to support mission-critical federal government programs.
The ideal candidate will have hands-on experience developing, fine-tuning, and deploying open-source language models to transform large volumes of unstructured text into actionable intelligence. This individual will apply advanced NLP and machine learning techniques to extract entities, identify relationships, perform high-fidelity extractive summarization, and develop automated solutions for processing complex, domain-specific documents.
The successful candidate will have experience working with models such as Llama 3, Mistral, and BERT, along with proficiency in Python, PyTorch, Hugging Face, and AWS GPU computing environments.
This role requires someone who can combine strong technical expertise with an understanding of mission requirements, working collaboratively with data engineers, developers, analysts, and government stakeholders in a secure, Agile development environment.
Key Responsibilities
Natural Language Processing & Machine Learning
• Design, develop, and implement advanced NLP solutions to process, analyze, and extract meaningful information from large volumes of unstructured text.
• Develop automated extractive summarization pipelines that identify, rank, and isolate critical information from complex documents while preserving the original source language.
• Implement Named Entity Recognition (NER) and relationship extraction techniques to identify and connect individuals, organizations, locations, events, and other mission-relevant entities.
• Fine-tune and adapt open-source LLMs, including Llama 3 and Mistral, using domain-specific datasets to improve model performance and relevance.
• Develop and optimize BERT-based models for high-precision entity extraction and classification.
• Apply machine learning techniques to improve information retrieval, sentence-level ranking, text classification, and automated document analysis.
• Evaluate model performance, accuracy, reliability, and confidence scoring to ensure high-quality analytical outputs.
AI/LLM Development & Cloud Infrastructure
• Develop, train, fine-tune, and deploy machine learning models within AWS cloud environments, including GPU-enabled computing infrastructure.
• Build scalable data processing and inference pipelines to support large-scale document ingestion and analysis.
• Utilize Python, PyTorch, Hugging Face, and related frameworks to develop and optimize AI/ML applications.
• Implement automated text cleaning, PDF parsing, document processing, and data transformation workflows.
• Maintain source code, modeling scripts, and development workflows using Git and GitHub.
Application Development & Mission Support
• Collaborate with software engineers, data engineers, analysts, and end-users to translate operational requirements into effective AI-driven solutions.
• Develop and integrate web-based applications and dashboards to visualize extracted information, relationship networks, summaries, and model confidence scores.
• Work with cross-functional teams to integrate NLP and LLM capabilities into existing systems and operational workflows.
• Support testing, troubleshooting, performance optimization, and continuous improvement of deployed models and applications.
• Document technical approaches, model configurations, data pipelines, and development processes.
Security & Agile Collaboration
• Ensure all development and deployment activities comply with applicable federal security requirements and data handling policies.
• Work effectively within secure government environments while protecting sensitive and mission-critical information.
• Participate in Agile/Scrum development activities, including sprint planning, technical discussions, and progress reviews.
Required Qualifications
• Active U.S. Secret Security Clearance.
• Bachelor's degree in Computer Science, Data Science, Mathematics, Statistics, Engineering, or a related technical field. (Equivalent relevant experience may be considered.)
• Demonstrated professional experience developing and implementing NLP and machine learning solutions.
• Hands-on experience working with open-source LLMs, including Llama, Mistral, or comparable models.
• Experience fine-tuning, adapting, and evaluating machine learning models using domain-specific datasets.
• Strong experience with Python and machine learning frameworks such as PyTorch and Hugging Face.
• Experience with Named Entity Recognition (NER), relationship extraction, text classification, and extractive summarization.
• Experience processing and analyzing unstructured data, including PDF documents and complex narrative text.
• Experience working with AWS cloud infrastructure, including EC2, S3, and GPU-enabled computing environments.
• Proficiency with Git-based version control and collaborative software development practices.
• Strong analytical, problem-solving, and communication skills.
Preferred Qualifications
• Experience supporting federal government, law enforcement, or intelligence community missions.
• Experience working with sensitive or classified datasets in secure environments.
• Experience developing AI/ML applications for investigative analysis, intelligence production, or large-scale document exploitation.
• Experience with model deployment, distributed inference, and scalable AI/ML architectures.
• Familiarity with information retrieval, knowledge graphs, network analysis, and entity resolution.
• Experience developing web-based applications or dashboards for analytical tools.
• Experience working in Agile/Scrum development environments.
Why Join Complete Data Solutions?
At CDS, you'll have the opportunity to work on challenging, mission-focused technology initiatives that make a meaningful impact. You'll collaborate with experienced professionals, apply emerging AI and machine learning technologies, and help develop innovative solutions supporting our federal government customers.
We believe in investing in our employees and offer a competitive compensation and benefits package, including:
• Competitive salary.
• Comprehensive health insurance.
• 401(k) retirement plan.
• Competitive paid annual leave.
• Tuition reimbursement.
• Additional employee benefits and professional development opportunities.
Equal Employment Opportunity
Complete Data Solutions is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, disability status, protected veteran status, or any other characteristic protected by applicable law.
Company: Complete Data Solutions (CDS)
Location: Merrifield, VA (On-Site)
Employment Type: Full-Time
Security Clearance: Active Secret Clearance Required
About Complete Data Solutions
Complete Data Solutions (CDS) is a leading data engineering and analytics company specializing in innovative solutions to complex data challenges for the federal government. For more than 25 years, CDS has proudly supported the Law Enforcement and Intelligence Communities, delivering advanced data engineering, analytics, system design and development, and reporting solutions.
At CDS, our employees are our greatest asset. We offer competitive salaries and a comprehensive benefits package, including health insurance, 401(k), competitive paid annual leave, tuition reimbursement, and additional benefits that reflect our long-term commitment to our employees' professional growth and well-being.
Position Overview
Complete Data Solutions is seeking an experienced Data Scientist specializing in Natural Language Processing (NLP) and Large Language Models (LLMs) to support mission-critical federal government programs.
The ideal candidate will have hands-on experience developing, fine-tuning, and deploying open-source language models to transform large volumes of unstructured text into actionable intelligence. This individual will apply advanced NLP and machine learning techniques to extract entities, identify relationships, perform high-fidelity extractive summarization, and develop automated solutions for processing complex, domain-specific documents.
The successful candidate will have experience working with models such as Llama 3, Mistral, and BERT, along with proficiency in Python, PyTorch, Hugging Face, and AWS GPU computing environments.
This role requires someone who can combine strong technical expertise with an understanding of mission requirements, working collaboratively with data engineers, developers, analysts, and government stakeholders in a secure, Agile development environment.
Key Responsibilities
Natural Language Processing & Machine Learning
• Design, develop, and implement advanced NLP solutions to process, analyze, and extract meaningful information from large volumes of unstructured text.
• Develop automated extractive summarization pipelines that identify, rank, and isolate critical information from complex documents while preserving the original source language.
• Implement Named Entity Recognition (NER) and relationship extraction techniques to identify and connect individuals, organizations, locations, events, and other mission-relevant entities.
• Fine-tune and adapt open-source LLMs, including Llama 3 and Mistral, using domain-specific datasets to improve model performance and relevance.
• Develop and optimize BERT-based models for high-precision entity extraction and classification.
• Apply machine learning techniques to improve information retrieval, sentence-level ranking, text classification, and automated document analysis.
• Evaluate model performance, accuracy, reliability, and confidence scoring to ensure high-quality analytical outputs.
AI/LLM Development & Cloud Infrastructure
• Develop, train, fine-tune, and deploy machine learning models within AWS cloud environments, including GPU-enabled computing infrastructure.
• Build scalable data processing and inference pipelines to support large-scale document ingestion and analysis.
• Utilize Python, PyTorch, Hugging Face, and related frameworks to develop and optimize AI/ML applications.
• Implement automated text cleaning, PDF parsing, document processing, and data transformation workflows.
• Maintain source code, modeling scripts, and development workflows using Git and GitHub.
Application Development & Mission Support
• Collaborate with software engineers, data engineers, analysts, and end-users to translate operational requirements into effective AI-driven solutions.
• Develop and integrate web-based applications and dashboards to visualize extracted information, relationship networks, summaries, and model confidence scores.
• Work with cross-functional teams to integrate NLP and LLM capabilities into existing systems and operational workflows.
• Support testing, troubleshooting, performance optimization, and continuous improvement of deployed models and applications.
• Document technical approaches, model configurations, data pipelines, and development processes.
Security & Agile Collaboration
• Ensure all development and deployment activities comply with applicable federal security requirements and data handling policies.
• Work effectively within secure government environments while protecting sensitive and mission-critical information.
• Participate in Agile/Scrum development activities, including sprint planning, technical discussions, and progress reviews.
Required Qualifications
• Active U.S. Secret Security Clearance.
• Bachelor's degree in Computer Science, Data Science, Mathematics, Statistics, Engineering, or a related technical field. (Equivalent relevant experience may be considered.)
• Demonstrated professional experience developing and implementing NLP and machine learning solutions.
• Hands-on experience working with open-source LLMs, including Llama, Mistral, or comparable models.
• Experience fine-tuning, adapting, and evaluating machine learning models using domain-specific datasets.
• Strong experience with Python and machine learning frameworks such as PyTorch and Hugging Face.
• Experience with Named Entity Recognition (NER), relationship extraction, text classification, and extractive summarization.
• Experience processing and analyzing unstructured data, including PDF documents and complex narrative text.
• Experience working with AWS cloud infrastructure, including EC2, S3, and GPU-enabled computing environments.
• Proficiency with Git-based version control and collaborative software development practices.
• Strong analytical, problem-solving, and communication skills.
Preferred Qualifications
• Experience supporting federal government, law enforcement, or intelligence community missions.
• Experience working with sensitive or classified datasets in secure environments.
• Experience developing AI/ML applications for investigative analysis, intelligence production, or large-scale document exploitation.
• Experience with model deployment, distributed inference, and scalable AI/ML architectures.
• Familiarity with information retrieval, knowledge graphs, network analysis, and entity resolution.
• Experience developing web-based applications or dashboards for analytical tools.
• Experience working in Agile/Scrum development environments.
Why Join Complete Data Solutions?
At CDS, you'll have the opportunity to work on challenging, mission-focused technology initiatives that make a meaningful impact. You'll collaborate with experienced professionals, apply emerging AI and machine learning technologies, and help develop innovative solutions supporting our federal government customers.
We believe in investing in our employees and offer a competitive compensation and benefits package, including:
• Competitive salary.
• Comprehensive health insurance.
• 401(k) retirement plan.
• Competitive paid annual leave.
• Tuition reimbursement.
• Additional employee benefits and professional development opportunities.
Equal Employment Opportunity
Complete Data Solutions is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, disability status, protected veteran status, or any other characteristic protected by applicable law.
group id: 10343194