AI Data & Knowledge Engineer: Build Semantic Pipelines

Apple Inc.; Cupertino (CA); Hybrid; USD 149,000 - 249,000; Full time

Job summary

Apple is seeking an AI Data & Knowledge Engineer in Cupertino to build data pipelines and knowledge layers for agentic AI applications, enabling scalable AI readiness and accurate context for chatbots and SIMPLified AI deployments.

You will design semantic layers, RAG-ready pipelines, and distributed data systems while collaborating with Analytics, Data Science, and business units. This role focuses on developing data infrastructure for AIML model training and deployment.

Qualifications

• Experience designing and building knowledge layers for AI systems, including knowledge graphs, RAG pipelines, and vector databases to ground LLM-driven applications in accurate, structured, unstructured and retrievable enterprise knowledge.
• Experience modeling enterprise knowledge and metadata within semantic layers to represent business entities, attributes, and their relationships.
• 5+ years of experience in designing, building, and maintaining scalable data solutions for large-scale analytics.
• Proficiency in SQL and development experience with cloud database environments like Snowflake, Redshift, Databricks.
• Proficiency in programming languages like Python, Java, R and open-source frameworks for distributed processing like Hadoop and Spark.
• Experience building data pipelines to ingest, transform, and continuously synchronize structured and unstructured enterprise data from multiple sources.
• Hands‑on experience using development tools in a modern cloud data stack for code management, versioning using Git, CI/CD tools, automation and orchestration using Apache Airflow or others and monitoring & alerting.
• Experience with Cloud platforms AWS, Azure or Google Cloud.

Responsibilities

• Responsible for the development and design of data pipelines and data knowledge layers for agentic AI applications.
• Design and implement data models for a semantic layer that integrates analytics data from multiple sources in an efficient and effective manner.
• Design and build scalable data and knowledge layers that power chatbots and other agentic applications.
• Build RAG-ready data pipelines and knowledge layers encompassing document ingestion, parsing, metadata tagging, embeddings, indexing with vector search.
• Design scalable architecture for semantic and hybrid search, knowledge graphs to enable contextually accurate text-to-SQL generation.
• Build mechanisms for incremental synchronization of data to knowledge updates so agent responses are current and reliable.
• Designing and operating distributed data systems — from SQL/NoSQL databases, Vector search, and orchestration.
• Collaborate with Analytics and Data Science teams to translate business requirements into reliable, actionable knowledge layers that support AI agent development and deliver targeted business outcomes.
• Collaborate with internal business partners, internal technology resources, external vendors, and partners.
• Play an active role in the development and maintenance of user documentation, including data models, mapping rules, and data dictionaries.
• Ensure data quality and accuracy by developing data validation and reconciliation processes.
• Build and maintain data pipelines for ingesting, processing, and transforming unstructured data sources, such as customer feedback, social media data, or sales call recordings.
• Develop data quality monitoring and validation processes specifically for AIML datasets, including identifying and addressing data bias.
• Work with data scientists to understand data requirements for AIML model training and deployment, ensuring data is available in the appropriate format and quality.
• Implement data governance policies and procedures to ensure the responsible and ethical use of data in AIML applications.

Skills

Data pipelines

Knowledge graphs

RAG pipelines

Vector databases

Python

SQL

Cloud platforms

REST/JSON

Tools

Snowflake

Redshift

Databricks

Hadoop

Spark

Airflow

Git

CI/CD

Job description

Apple is seeking an AI Data & Knowledge Engineer in Cupertino to build data pipelines and knowledge layers for agentic AI applications, enabling scalable AI readiness and accurate context for chatbots and SIMPLified AI deployments.

You will design semantic layers, RAG-ready pipelines, and distributed data systems while collaborating with Analytics, Data Science, and business units. This role focuses on developing data infrastructure for AIML model training and deployment.