A

Accenture

Advises businesses and runs their technology

Knowledge Engineering Semantic Expert

Data EngineeringUpdated on Nov 8
Full-time

About the Job

Requirements

  • A minimum of 5 years of hands-on experience in Big Data engineering, data engineering, or analytics engineering, including developing scalable ETL/ELT pipelines for batch and/or streaming workloads.
  • At least 2 years of Python experience, including hands-on use of relevant libraries and frameworks such as PySpark, RDFLib, NetworkX, and FastAPI.
  • At least 2 years of experience with graph query and data languages such as SPARQL, Cypher, RDF, and/or SQL.
  • At least 2 years of experience with knowledge graph and graph database technologies, including platforms such as Neo4j, Stardog, GraphDB, and/or Amazon Neptune.

Responsibilities

  • Architect, develop, and implement production knowledge graph solutions using RDF triple stores and/or property graph technologies.
  • Translate semantic architectures, ontologies, and enterprise data models into scalable technical implementations.
  • Build automated data ingestion and transformation pipelines using Python and PySpark to map relational, document, streaming, and unstructured data into graph representations.
  • Design and implement identity resolution, entity disambiguation, entity linking, and link prediction capabilities to create unified, canonical graph records at enterprise scale.
  • Integrate graph databases with enterprise data lakes, lakehouses, analytics platforms, APIs, and downstream applications.
  • Develop high-throughput REST, GraphQL, and/or gRPC services that expose graph traversal, semantic search, and graph query capabilities.
  • Design and implement GraphRAG and hybrid vector-graph solutions that ground Large Language Models using contextual enterprise knowledge.
  • Develop integration layers that connect knowledge graphs, vector stores, enterprise data platforms, and Generative AI applications.
  • Build data processing and retrieval capabilities that enable LLMs and AI agents to leverage trusted, contextualized enterprise information.
  • Partner with AI, data, ontology, and application engineering teams to operationalize knowledge-driven AI solutions.
  • Leverage Databricks, Apache Spark, or comparable technologies to perform distributed graph transformations, large-scale entity resolution, and semantic data processing.
  • Develop production-grade ETL/ELT pipelines supporting batch, streaming, structured, semi-structured, and unstructured data.
  • Create automated testing, schema validation, and data-quality frameworks using technologies and approaches such as SHACL and Cypher constraints.
  • Profile and optimize SPARQL, Cypher, and/or Gremlin query execution for high-volume and high-concurrency environments.
  • Design indexing, caching, partitioning, and query optimization strategies to improve graph performance and scalability.
  • Establish CI/CD practices for ontology and graph deployments, version control, automated testing, and infrastructure-as-code across cloud environments.
  • Design solutions for high availability, low latency, scalability, observability, and production resiliency.
  • Mentor senior and mid-level engineers in knowledge graph engineering, Python development, distributed data processing, and performance optimization.

Desired Qualifications

  • Hands-on experience with Databricks or comparable modern data platforms, including PySpark, Spark SQL, Delta Lake, Snowflake, Unity Catalog, and/or enterprise lakehouse architectures.
  • Experience developing lakehouse-to-graph ingestion pipelines and large-scale semantic data transformation workloads.
  • Experience implementing GraphRAG, Retrieval-Augmented Generation (RAG), vector search, and hybrid vector-graph architectures for Generative AI applications.
  • Experience with SHACL, graph schema validation, ontology versioning, and semantic data-quality frameworks.
  • Experience implementing RDF and/or property graph architectures in production environments.
  • Experience with regulatory or compliance-driven modeling.
  • Graph-based machine learning alongside symbolic modeling.

About the Company

Accenture

Advises businesses and runs their technology

Accenture advises large businesses and public agencies on strategy, builds their technology systems and runs ongoing operations. Its teams connect business planning with implementation, covering areas such as cloud migration, cybersecurity and customer experience. Consultants work with clients to redesign processes, while engineers integrate software from technology partners and maintain the resulting systems for multinational organizations. Clients pay for project work or continuing services, including application support and business processes such as finance and customer service. Accenture was founded in 1989 and has its headquarters in Dublin, Ireland.

Company size
10,001+
Company stage
IPO
Headquarters
Dublin, Ireland
Founded
1989

Recently Posted Jobs

Explore more opportunities at Accenture

See more jobs