Backend Engineer, AI Context & Semantics

Workday; Pleasanton (CA); On-site; USD 140,000 - 190,000; Full time

Job summary

Workday in Pleasanton, CA is seeking a Software Development Engineer in Context and Semantics to help power our AI Agents and enterprise data integration. You will join a backend-focused team building scalable data infrastructure and connect large language models to complex data stores.

You will implement RAG pipelines, vector database integrations, and query federation services while upholding security, reliability, and fast data access across the platform.

Qualifications

• 3+ years of backend software engineering experience.
• 2+ years of hands-on programming in Java, Python, Scala, or Go.
• 1+ year of exposure to AI/ML concepts, LLM APIs, vector databases, or RAG architectures.

Responsibilities

• Design, develop, and test scalable backend microservices, APIs, and data pipelines powering the context and semantic layer for AI Agents.
• Build and maintain enterprise RAG pipelines, including embedding workflows, document chunking strategies, and vector database integrations (e.g., Pinecone, Milvus, Elasticsearch).
• Develop distributed query execution features (e.g., Trino) to retrieve enterprise data securely for LLMs.
• Implement orchestration logic and context‑management components using AI frameworks (e.g., LlamaIndex, LangChain) for multi‑turn agent interactions.
• Ensure code adheres to data privacy, tenant isolation, and RBAC standards.
• Write unit and integration tests; participate in code reviews and maintain high reliability and monitoring.
• Collaborate with Senior Engineers, Product Managers, and leads to translate requirements into code.

Skills

Backend development

Java/Python/Scala/Go

AI/ML concepts

Education

Bachelor’s degree in CS/Software Engineering

Master’s degree preferred

Tools

Trino/LDQ

Pinecone

Milvus

Elasticsearch

LlamaIndex

LangChain

Job description

Workday in Pleasanton, CA is seeking a Software Development Engineer in Context and Semantics to help power our AI Agents and enterprise data integration. You will join a backend-focused team building scalable data infrastructure and connect large language models to complex data stores.

You will implement RAG pipelines, vector database integrations, and query federation services while upholding security, reliability, and fast data access across the platform.