Job description
Job Description & Summary
The opportunity
Provide trusted, contextual and well-governed enterprise data and knowledge services that ground agentic workflows and improve their reliability.
What you will be doing
· Design and build ingestion, transformation and serving pipelines for structured and unstructured data.
· Create retrieval indexes, metadata models, semantic layers, knowledge graphs or data products as appropriate.
· Implement chunking, enrichment, lineage, quality and access-control patterns.
· Optimize retrieval quality, freshness, latency and cost with the AI engineering team.
· Integrate cloud and on-premises data sources for hybrid solutions.
· Support evaluation datasets, monitoring data and traceability requirements.
What we need from you
· 4+ years in data engineering, analytics engineering, information retrieval or knowledge platforms.
· Strong SQL and Python skills and experience with data pipelines, APIs and data modeling.
· Practical knowledge of vector search, embeddings, metadata, document processing and retrieval evaluation.
· Experience with enterprise security, data quality and hybrid data integration.
Relevant AI technologies and tooling
· Strong SQL and Python capability with practical experience in Spark and data engineering platforms such as Microsoft Fabric, Azure Data Factory, Databricks, Snowflake or equivalent.
· Hands-on experience processing structured and unstructured content, including parsing, OCR, chunking, enrichment, metadata extraction, lineage and incremental indexing.
· Experience with vector and hybrid search technologies such as Azure AI Search, PostgreSQL with pgvector, Elasticsearch, Pinecone, Weaviate, Milvus or equivalent.
· Understanding of embedding selection, semantic and lexical retrieval, metadata filtering, reranking, query transformation, evaluation datasets and retrieval quality metrics.
· Experience with graph and knowledge technologies such as Neo4j, RDF or property graphs, ontologies, entity resolution and GraphRAG patterns is desirable.
· Ability to implement secure hybrid data access, row or document-level permissions, data masking and traceable ingestion from cloud and on-premises repositories.
Measures of success
· Data freshness, quality and availability
· Retrieval relevance and traceability
· Speed of onboarding new knowledge sources
· Pipeline reliability and performance
· Compliance with data-access requirements
Key interfaces
· Other members of the AI Transformation & Agentic Systems Practice
· PwC sector, functional, cloud, cyber, risk, Responsible AI and change specialists
· Client business owners, product owners, technology teams and operational users
· Technology alliance and implementation partners where relevant
Contribution to the practice
· Support proposals, client workshops and market development appropriate to seniority.
· Contribute reusable methods, patterns, code, assets and lessons learned.
· Coach colleagues and participate in the capability’s continuous learning agenda.
· Uphold PwC quality, independence, confidentiality and risk-management requirements.
#LI-BS1 #LI-Hybrid