NLP Engineer - Clearance Required

What you will do in this role:

As a NLP Engineer at BTI360, you will:

• Lead end-to-end knowledge graph and knowledgebase development efforts from problem definition to production, designing pipelines that extract, normalize, link, and organize information into scalable graph-based systems. 
• Design and evaluate extraction and resolution workflows using sound methodologies and fit-for-purpose metrics to assess entity extraction, linking, relationship quality, and overall knowledgebase completeness and accuracy. 
• Translate business requirements into quantitative problems and communicate technical findings to both technical and non-technical stakeholders through reports, presentations, and direct customer engagement. 
• Drive technical decision-making for schema design, ontology alignment, extraction approaches, and graph architecture based on mission needs, data quality, and long-term maintainability. 
• Stay current with advances in knowledge representation and information extraction and introduce practical techniques, tools, and frameworks that improve graph construction, curation, and analytic value. 
• Apply analytical and statistical methods to validate extracted insights, measure data quality, and support confident decision-making from structured and unstructured sources. 
• Develop reports and whitepapers that evaluate solution alternatives based on impact, cost, technical feasibility, and alignment with strategic goals. 
• Collaborate across teams to align on strategy, provide data science expertise, and contribute to proposals and strategic initiatives.  
• Mentor junior data scientists by providing technical guidance, defining project direction, and sharing best practices in graph-oriented data modeling, extraction workflows, and knowledgebase stewardship. 

You may thrive in this role if you have the following skills:

• Active Security Clearance (Secret or higher) or the ability to obtain one
• 5+ years of experience in data science or machine learning roles with demonstrated impact on production systems. 
• Deep expertise in natural language processing (NLP) techniques 
• Experience building Knowledge Graphs using Resource Description Framework (RDF) or Labeled Property Graph (LPG) models, including schema/ontology design 
• Experience with Knowledge Graph construction pipelines: rule- and LLM-based Named Entity Recognition (NER), Relation Extraction (RE), Entity Normalization and Disambiguation/Linking 
• Proven track record of model evaluation using appropriate metrics and methodologies for different problem types (precision/recall, silhouette scores, benchmarks, etc.) 
• Strong scripting skills with experience in AI/ML frameworks (scikit-learn, PyTorch/TensorFlow, transformers) and data manipulation libraries, including proficiency with Jupyter notebooks for exploratory analysis and experimentation 
• Basic software engineering practices such as git, CI/CD, code reviews, documentation, and ability to access and leverage remote APIs
• Comfortable working in cloud platforms (AWS, Azure, GCP) 
• Excellent communication skills with experience translating technical metrics into business value and presenting findings to leadership and customers 
• Ability to work independently 
• Candidates must maintain a primary residence within a two‑hour drive of Herndon, VA to support onsite collaboration as needed. 
   

You may excel in this role if you have the following skills:

• Strong Python programming skills 
• Experience with Graph RAG (Retrieval-Augmented Generation): hybrid retrieval across graph traversal and dense/sparse vector search
• Experience with large or multimodal datasets
• Experience leading technical initiatives