Experience:

• 2–5 years of software engineering experience
• 1–2 years focused on GenAI / LLM application development

Responsibilities:

• Design, build, and maintain LLM-powered application components
• Develop and optimize RAG pipelines including chunking, vector store management, embedding tuning, and retrieval relevance evaluation
• Build and maintain multi-agent orchestration workflows using LangChain, LangGraph, or equivalent frameworks
• Implement context graph solutions for semantic understanding and cross-entity reasoning in supply chain domains
• Design and integrate Azure AI services including Azure OpenAI, Azure AI Search, Azure Machine Learning, and related PaaS components
• Contribute to prompt engineering best practices and LLM evaluation frameworks
• Incorporate information security, responsible AI, and data privacy considerations into development
• Understand impact of GenAI component changes on downstream agents and end-customer experiences

Additional responsibilities:

• Participate in team ceremonies such as backlog grooming, sprint planning, daily stand-ups, and retrospectives
• Identify and escalate production issues with LLM agents with relevant context
• Plan and perform routine changes to agent configurations, prompt templates, and model version upgrades
• Resolve incidents within defined GenAI service functions including model fallback and latency issues
• Handle service requests related to agent onboarding, tool integration, and knowledge base updates

More skills:

TypeScript, JavaScript, Retrieval-Augmented Generation (RAG), Weaviate, Pinecone, context graphs, knowledge graphs, system prompt design, few-shot prompting, chain-of-thought techniques, LLM evaluation strategies, hallucination detection, faithfulness scoring, output quality metrics

Other:

• Collaborate with product engineers, data scientists, and platform architects
• Work within Blue Yonder engineering standards and clean code principles
• Company values emphasize diversity and equal opportunity employment