Principal Investigator / Principal AI & Technical Data Scientist

Principal Investigator / Principal AI & Technical Data Scientist

Topic Title: Tech Data Interactive Electronic Technical Manuals Convertor

Education: PhD Required

Arch Systems is seeking a Principal Investigator (PI) to lead applied R&D for an AI-enabled technical-data transformation capability that converts heterogeneous legacy technical manuals into structured, standards-compliant, traceable XML/IETM technical data. The PI will lead research spanning multimodal document intelligence, NLP/OCR, semantic reconstruction, canonical technical-data modeling, S1000D/IETM transformation, provenance, AI assurance, and authoritative technical-data retrieval.

Key Responsibilities

·       Provide scientific and technical leadership for AI-enabled legacy technical-manual transformation.

·       Lead research in multimodal document understanding, OCR/NLP, semantic reconstruction, knowledge representation, and structured technical-data generation.

·       Define approaches for converting PDF, scanned, XML/SGML and legacy military technical data into canonical technical objects and target IETM/XML structures.

·       Guide S1000D/IETM, XML/XSD, BREX/Schematron, technical-publication and validation architecture.

·       Design quantitative feasibility experiments covering extraction accuracy, semantic fidelity, provenance, standards compliance, retrieval accuracy and correction effectiveness.

·       Ensure AI-generated candidate interpretations remain evidence-grounded and that authoritative technical output is controlled through deterministic rules, validation and human review.

·       Lead technical interaction with Government stakeholders and support SBIR technical reporting, demonstrations, publications and Phase II transition planning.

Required / Preferred Qualifications:

·        Ph.D. strongly preferred in Computer Science, AI/ML, NLP, Information Science, Computer/Systems/Electrical Engineering, or related discipline

·        8–15+ years of relevant technical/R&D experience; demonstrated expertise in document AI/NLP and structured technical data; strong Python/AI/ML background; experience with XML and schema-based transformation/validation.

·        S1000D, IETM/IETMS, CSDB, BREX, MIL-STD technical data and Navy maintenance/technical-publication experience are highly desirable.

·        Previous NAVSEA/NAVAIR/NAWC/NSWC/NAVWAR/ONR or DoD R&D/SBIR PI experience is a major advantage. Relevant patents and peer-reviewed publications are preferred.