Principal Knowledge & Data Architect

Howard Hughes Medical Institute Hhmi

🌍 Удалённо

Senior

Полная занятость

🌐 Глобал

Продуктовая

Tech

Описание вакансии

Обязанности

•Build chunking and embedding pipelines

•Build retrieval-augmented generation pipelines

•Debug and rebuild production RAG pipeline failures

•Define AI knowledge requirements for data integrations

•Design and run retrieval and re ranking

•Design content capture and classification

•Design knowledge graph data model

•Explain technical architecture trade offs to stakeholders

•Extract structure from unstructured content

•Implement knowledge classification and lineage governance

•Operate entity resolution and deduplication

•Own knowledge management architecture

•Stand up and operate knowledge graphs

Условия

•Benefits including health and wellness programs

•Health, wellness, and retirement plans

Технологии: AWS Neptune, Canonicalization, Chunking, Cypher, DBT, Databricks, Deduplication, ETL, Embeddings, Entity Resolution, Graph Databases, Gremlin, Hybrid retrieval, Indexing, Information Extraction, Knowledge graphs, LLM, LLM based extraction, Language Processing, Natural Language, Natural Language Processing, Neo4j, PGVector, Pinecone, Python, Qdrant, Query rewriting, Re-ranking, Retrieval-Augmented Generation, SPARQL, SQL, Vector Databases, Weaviate