Parsing Architect (AI) - SME
Core
Design, scale, and govern enterprise-level parsing and document preprocessing architecture for autonomous agents and LLM application stacks, ensuring reliable data processing pipelines from unstructured data lakes.
Role type
Senior IC Parsing Architect (AI)
Builds
Resilient data streaming pipelines, unified semantic data schemas, and high-assurance retrieval infrastructure for hybrid search.
Domain
AI/LLM infrastructure, data governance, and federal security compliance
Deliverable
production ML models
Required skills
Parsing architecture design, OCR and vision-language model orchestration, data ingestion and segmentation, vector database integration, metadata tagging protocols, PII/PHI filtering, data governance frameworks
Preferred skills
GraphRAG implementation, layout engine evaluation, cost-optimized streaming pipeline design
Technologies
OCR, vision-language models, vector databases, GraphRAG
Responsibilities
Design end-to-end parsing frameworks, evaluate cutting-edge parsing technologies, build data streaming pipelines, define semantic schemas and chunking rules, architect retrieval infrastructure, establish access controls for hybrid search, collaborate on data lineage and compliance
Seniority
Senior, hands-on IC
