Senior AI Backend Engineer: Context & Semantics

Workday; Pleasanton (CA); On-site; USD 190,000 - 285,000; Full time

Job summary

Workday in Pleasanton, CA is seeking a Senior Software Development Engineer in Context and Semantics to lead the backend that powers our AI Agents. You will design, code, and scale services that connect foundational models to enterprise data. You will craft advanced RAG pipelines, implement vector search, and develop query federation layers.

You will mentor teammates and help set engineering standards. The role blends distributed data engineering with applied AI in a fast-growing,

Qualifications

• 8+ years in backend or distributed systems engineering.
• 5+ years coding in Java, Python, Scala, or Go.
• 1+ year building production-grade LLM apps, RAG pipelines, or vector search.
• Experience with enterprise data and security considerations.

Responsibilities

• Architect, build, and deploy backend services, APIs, and data pipelines for Workday’s AI Agents.
• Design and optimize enterprise-grade RAG pipelines with embedding generation and vector DB integration.
• Build distributed query layers (e.g., Trino) to fetch and translate context across systems and data lakes.
• Develop LLM orchestration workflows using LangChain, LlamaIndex, or similar frameworks.
• Embed data privacy, tenant isolation, and RBAC into retrieval and context layers.
• Optimize architectures for low-latency retrieval and high-throughput LLM interactions.
• Mentor engineers, lead code/design reviews, and establish best practices for this product area.

Skills

Backend engineering

Programming: Java/Python/Scala/Go

LLM/RAG pipelines

Vector search

Knowledge graphs

Education

Bachelor’s degree in CS/SE

Master’s degree preferred

Tools

Trino/Presto

Spark

LangChain

LlamaIndex

Semantic Kernel

Pinecone

Milvus

Elasticsearch

Job description

Workday in Pleasanton, CA is seeking a Senior Software Development Engineer in Context and Semantics to lead the backend that powers our AI Agents. You will design, code, and scale services that connect foundational models to enterprise data. You will craft advanced RAG pipelines, implement vector search, and develop query federation layers.

You will mentor teammates and help set engineering standards. The role blends distributed data engineering with applied AI in a fast-growing,