Senior Data Engineer - Knowledge Graphs
Role details
Job location
Tech stack
Job description
Peraton Labs is seeking a Senior Data Engineer to help design, build, and operationalize the data foundations supporting advanced AI-enabled capabilities. This role will focus on transforming complex structured and unstructured information into graph-aware, semantically meaningful data products that can support analytics, reasoning, retrieval, and agentic workflows., Design, build, and maintain scalable data pipelines supporting graph-based and AI-enabled workflows
- Develop data models and processing approaches that transform raw structured and unstructured data into semantically meaningful graph-oriented representations
- Contribute to the creation, enrichment, and operationalization of knowledge graphs supporting retrieval, reasoning, entity relationships, and advanced analytics
- Support ingestion, normalization, linking, and transformation of data into graph-compatible formats such as RDF and related semantic representations
- Apply experience in areas such as NLP, AMR, UMR, semantic parsing, graph analysis, or ontology-informed data modeling to improve how information is structured and connected
- Build data pipelines and engineering workflows that support graph-centric applications, including AI-enabled search, contextual retrieval, and decision support
- Partner with AI/ML, platform, and software engineering teams to ensure graph and semantic data assets are usable within production-oriented systems
- Help define approaches for entity resolution, relationship extraction, semantic enrichment, metadata management, and graph quality validation
- Contribute to architectures that support agentic AI workflows by enabling richer data context, structured memory, and relationship-aware information access
- Work with a mix of structured, semi-structured, and unstructured data sources to improve interoperability and downstream usability
- Support graph analysis and exploration efforts that inform system design, data relationships, and capability development
- Ensure data engineering solutions are maintainable, scalable, and aligned to operational and mission needs
- Document data flows, graph models, transformation logic, and engineering decisions clearly for technical stakeholders
Requirements
We are looking for a candidate who combines strong data engineering execution with meaningful experience in knowledge graphs, semantic representations, NLP-derived structure, and graph-based analysis. This may come from a traditional data engineering background with hands-on knowledge graph experience, or from a research-oriented knowledge graph / semantic systems background paired with proven implementation ability.
The ideal candidate for this role should be comfortable working across data pipelines, semantic modeling, graph representations, and AI-enabled data architectures. You should be comfortable moving between concept and implementation, helping shape how knowledge is extracted, structured, linked, and made usable for downstream AI systems., * Minimum of BS with 12+ years of experience, MS with 10+ YoE, or PhD with 7+ YoE in data engineering, knowledge graph engineering, semantic systems, NLP-enabled data processing, or related technical roles
- Strong hands-on experience building and maintaining data pipelines in modern engineering environments
- Demonstrated experience with knowledge graphs, graph data models, or semantic data architectures
- Experience within one or more of the following areas: RDF, graph analysis, semantic representation, ontology-informed data modeling, AMR, UMR, or NLP-driven structured extraction
- Strong hands-on experience with Python, JavaScript/TypeScript, and SQL for data transformation and pipeline development, plus familiarity with graph and semantic tooling such as Neo4j/Neptune/GraphDB platforms
- Experience working with both structured and unstructured data in support of downstream analytics or AI/ML use cases
- Ability to translate complex source data into usable, high-quality representations for graph-based or semantic systems
- Strong understanding of data quality, schema design, metadata, transformation logic, and scalable data workflows
- Ability to operate effectively in highly technical environments where requirements may evolve and where both rigor and adaptability matter
- Strong written and verbal communication skills, with the ability to explain technical tradeoffs clearly across engineering and non-engineering stakeholders
- US Citizenship is a requirement for this position, * Experience with agentic AI systems or workflows that rely on structured context, memory, planning, or relationship-aware retrieval
- Experience with GraphRAG or related graph-enhanced retrieval architectures
- Familiarity with graph databases, triplestores, semantic query languages, or related tooling
- Experience supporting entity resolution, relationship extraction, semantic search, or contextual retrieval workflows
- Background in NLP, semantic parsing, knowledge representation, or computational linguistics
- Experience designing systems that connect knowledge representation approaches to operational AI applications
- Familiarity with ontology development, schema alignment, or semantic interoperability challenges
- Exposure to mission, government, defense, or regulated technical environments
- Advanced degree in computer science, data science, computational linguistics, AI/ML, or a related field