Data & Knowledge Engineer

Description

The team provides trusted, context-aware and governed data and knowledge services that ground agentic workflows and make them more dependable.

This role sits in the AI Transformation & Agentic Systems Practice.

Success is measured by data freshness, quality and availability, retrieval relevance and traceability, how quickly new knowledge sources are onboarded, pipeline reliability and performance, and compliance with data-access rules.

Responsibilities

• Build pipelines that ingest, transform and serve both structured and unstructured data.
• Create retrieval indexes, metadata models, semantic layers, knowledge graphs or data products, depending on what each case needs.
• Apply chunking, enrichment, lineage, quality checks and access-control patterns.
• Tune retrieval quality, data freshness, latency and cost together with the AI engineering team.
• Connect cloud and on-premises data sources for hybrid solutions.
• Maintain evaluation datasets, monitoring data and traceability records.
• Work with practice colleagues, the firm's sector, functional, cloud, cyber, risk, Responsible AI and change specialists, client business owners, product owners, technology teams, operational users and alliance partners.
• Support proposals, client workshops and market development at your level of seniority.
• Share reusable methods, patterns, code, assets and lessons learned, coach colleagues and keep learning.
• Meet the firm's quality, independence, confidentiality and risk-management requirements.

Requirements

• 4+ years in data engineering, analytics engineering, information retrieval or knowledge platforms.
• Solid SQL and Python, with experience in pipelines, APIs and data modelling.
• Working knowledge of vector search, embeddings, metadata, document processing and retrieval evaluation.
• Experience with enterprise security, data quality and hybrid data integration.
• Strong SQL and Python, with practical Spark work and data platforms such as Microsoft Fabric, Azure Data Factory, Databricks, Snowflake or equivalent.
• Hands-on work with structured and unstructured content, covering parsing, OCR, chunking, enrichment, metadata extraction, lineage and incremental indexing.
• Experience with vector and hybrid search tools such as Azure AI Search, PostgreSQL with pgvector, Elasticsearch, Pinecone, Weaviate, Milvus or equivalent.
• Understanding of embedding choice, semantic and lexical retrieval, metadata filtering, reranking, query transformation, evaluation datasets and retrieval quality metrics.
• Ability to set up secure hybrid data access, row or document-level permissions, data masking and traceable ingestion from cloud and on-premises repositories.
• Desirable: experience with graph and knowledge technologies such as Neo4j, RDF or property graphs, ontologies, entity resolution and GraphRAG patterns.

Conditions

Hybrid working arrangement (LI-BS1).