Knowledge Engineer - Generative AI Platform and Cortex

Peraton•,

7d•$135,000 - $216,000

About The Position

Peraton Labs is seeking a Senior Knowledge Engineer to serve as the program-embedded owner of the knowledge layer that powers a customer-deployed Generative AI Platform. This role sits at the intersection of knowledge engineering, data governance, and customer-facing enablement — keeping the program’s Cortex (knowledge graph, ontology, and curated content) clean, coherent, and connected, and acting as the trusted technical partner to the sector personnel who manage data on the ground. The position is broad-based and applicable across mission and non-mission domains alike (operations, program management, customer experience, supply chain, finance, compliance, engineering performance, and beyond). This individual is the program’s knowledge manager, librarian, and connection-maker. They govern what enters the data lake, define how content is described and linked, curate the Cortex and its ontology, and ensure that the relationships between entities, sources, and concepts reflect the way the program actually operates. They translate fluent domain understanding into a living, queryable knowledge structure that analysts, developers, and customer stakeholders can rely on. As a senior individual contributor, this role sets standards, drives consensus, and mentors others. The Senior Knowledge Engineer works alongside the Data Architect and platform engineering team to ensure the knowledge layer evolves coherently with the underlying data architecture, and provides direct, mission-grounded feedback on platform capabilities and gaps. The ideal candidate brings deep experience in ontology and taxonomy design, knowledge graphs, content curation, and data stewardship — combined with the customer-facing presence to coach sector data managers and represent the program with credibility.

Requirements

Minimum of a Bachelor’s degree in Information Science, Library & Information Science, Computer Science, Data Science, Knowledge Management, Linguistics, Computational Linguistics, or a related field; Master’s degree preferred.
8–12 years of relevant experience in knowledge engineering, ontology/taxonomy development, knowledge graph curation, data stewardship, information architecture, or comparable senior knowledge-management roles.
Demonstrated experience designing and maintaining ontologies, taxonomies, and controlled vocabularies in production environments — not just as one-time deliverables.
Demonstrated experience curating and governing a knowledge graph or comparable structured knowledge asset, including entity resolution, relationship modeling, and ontology change management.
Demonstrated experience governing data intake into a lake, warehouse, or comparable repository — including source onboarding, metadata standards, classification, and quality gates.
Strong grounding in data stewardship and governance practices — business glossaries, lineage, provenance, retention, and access control — with the ability to apply them pragmatically.
Working proficiency in SQL and a scripting language (Python preferred) sufficient to inspect data, profile sources, validate curation outcomes, and automate routine knowledge-engineering tasks.
Familiarity with knowledge representation standards and tooling (e.g., RDF, OWL, SKOS, SHACL, property graphs, Cypher/Gremlin, or comparable) and pragmatic judgment about when to apply them.
Strong critical thinking and problem-solving skills, including the ability to reconcile conflicting source definitions, resolve ambiguity, and impose structure on messy unstructured content without losing fidelity.
Customer-facing presence and judgment — the ability to coach sector data managers, build trust quickly, and represent the program professionally.
Strong written and verbal communication skills, including the ability to brief executive and customer audiences and to author clear specifications, standards, and methodology documents.
Comfort operating in fast-paced, evolving environments where tools, ontologies, and workflows are actively being developed and refined.
Ability to work cross-functionally with architects, developers, and analysts, and to provide clear, prioritized feedback on platform capabilities and knowledge-engineering needs.
US Citizenship with the ability to obtain and maintain required security clearances or suitability determinations as the program requires.

Nice To Haves

Hands-on experience with AI-enabled platforms, large language models, retrieval-augmented generation (RAG), agentic AI workflows, or AI-assisted curation and enrichment workflows.
Experience curating knowledge for LLM consumption — chunking strategies, embedding hygiene, retrieval evaluation, and grounding/citation discipline.
Experience with graph databases (Neo4j, Kuzu, Amazon Neptune, TigerGraph, or comparable) and graph query languages (Cypher, Gremlin, SPARQL).
Experience with metadata management, data catalog, or governance platforms (Collibra, Alation, Atlan, DataHub, Apache Atlas, or comparable).
Familiarity with formal knowledge-management frameworks (DAMA-DMBOK, DCAM, FAIR data principles) and the judgment to apply them pragmatically.
Experience with NLP techniques relevant to knowledge engineering — named entity recognition, relation extraction, coreference resolution, topic modeling — at a working rather than research level.
Background in domains beyond intelligence — such as commercial operations, federal civilian programs, healthcare, financial services, supply chain, customer experience, or engineering program management — where knowledge rigor and customer trust are equally critical.
Experience embedding with a customer or program team for an extended period and being recognized as a trusted advisor rather than an external contributor.
Experience developing ontology style guides, curation SOPs, intake standards, training materials, or knowledge-engineering playbooks.
Experience evaluating or adopting new knowledge-engineering or AI tooling, including participation in pilot programs, technology transitions, or capability assessments.
Mentorship experience — coaching junior knowledge engineers, curators, or stewards and contributing to team growth.
Exposure to Agile delivery, sprint-based curation cadences, and cross-functional team collaboration.

Responsibilities

Own the health and integrity of the program’s Cortex — governing the knowledge graph, ontology, taxonomies, controlled vocabularies, and curated content that the Generative AI Platform draws on.
Design, evolve, and maintain the ontology and taxonomy: define entities, relationships, properties, and controlled vocabularies that reflect how the program and its customer actually operate.
Govern data-lake intake — establish and enforce standards for source onboarding, metadata, classification, tagging, quality gates, and retention; decide what enters the lake and Cortex, and on what terms.
Identify and maintain the connections that make the knowledge layer valuable — cross-source linkages, master/reference data alignment, entity resolution, and relationship enrichment across structured and unstructured content.
Serve as the program’s knowledge manager and librarian — own the business glossary, content findability, citation discipline, and the lifecycle of knowledge assets from acquisition through retirement.
Curate Cortex content: deduplicate, retire stale material, manage manifest accuracy, control ontology drift, and ensure provenance and lineage are captured and traceable.
Provide technical support and coaching to sector personnel who manage data on the ground — helping them publish to standards, troubleshoot data issues, and adopt the metadata and tagging practices that keep the knowledge layer trustworthy.
Act as the trusted advisor on knowledge architecture decisions — assess current state, identify future state, conduct gap analysis, and recommend prioritization that aligns the knowledge layer to program objectives.
Collaborate with the Data Architect and platform engineering team to ensure the ontology, knowledge graph, and curation practices integrate cleanly with the underlying data architecture, pipelines, and retrieval systems.
Partner with analysts (all-source, data, and research) to understand how knowledge is consumed, surface gaps in coverage or connections, and continuously improve retrieval relevance and analytical productivity.
Define and enforce knowledge-engineering standards, style guides, and SOPs — including ontology change management, naming conventions, source descriptions, and curation workflows.
Drive consensus across business and technical stakeholders on the knowledge architecture vision, roadmap, and tradeoffs; influence the program and customer to make sound long-term decisions.
Provide continuous, well-articulated feedback to platform engineering and product teams on capability gaps, retrieval quality, ontology tooling, and curation workflows that would unlock additional program value.
Document the knowledge architecture, ontology decisions, intake standards, and curation methodologies so the capability is transferable and not dependent on a single individual.
Mentor junior knowledge engineers, data curators, and data stewards; build the program’s knowledge-engineering bench through coaching, code/model review, and shared best practices.
Support training and onboarding of analysts, engineers, and sector personnel on how to use, contribute to, and trust the Cortex.
Meets directly with program leadership, sector data managers, and customer stakeholders to identify knowledge needs, intake priorities, and curation requirements.
Works within overall program plans and delivery cadences; aligns ontology and curation work to platform release cycles.
Provides feedback to customers and creates structured documentation, including ontology specifications, intake standards, curation playbooks, and status reports.
Advises program and customer leadership on knowledge-architecture configuration and implementation options based on industry best practices.
Leads or supports the customization, implementation, testing, and deployment of ontology updates, taxonomy changes, and Cortex curation workflows.
Acts as a technical mentor for the program team and customer in transferring knowledge-engineering expertise.
Ensures that knowledge-engineering deliverables are complete, traceable, and timely.
Generates timely status reporting on Cortex health, intake throughput, curation backlogs, and knowledge-quality metrics.