Interviewing Process: 2 rounds _ R1: Tech with 724software & R2: Tech with client (Optional)
. Data Engineer (Ontology-driven AI Integration)
Experience: 510 years
Requirements:
Shall design and implement ontology-driven data models that support structured knowledge representation across AI and SaaS workflows.
Shall be proficient in AWS services: SageMaker, Bedrock, Neptune, Glue, and Athena, with strong knowledge of pipelines and orchestration (Step Functions, Lambda).
Shall develop and maintain ETL/ELT pipelines that ingest unstructured and structured data (PDFs, OSINT, RFPs, relational data).
Shall design knowledge graphs and vector stores (Neptune, OpenSearch, pgvector) to support semantic search and RAG pipelines.
Shall collaborate with AI/ML engineers to integrate ontologies into LLM workflows for better grounding, retrieval, and context injection.
Shall enforce data quality, governance, and compliance, with specific attention to GovCloud/FedRAMP/CUI requirements.
Shall optimize query performance across structured and unstructured datasets for both analytics and real-time inference.
Nice to have: Experience with ontology frameworks (OWL, RDF, SKOS) and domain-specific modeling for capture/proposal workflows.
