This list contains only the countries for which job offers have been published in the selected language (e.g., in the French version, only job offers written in French are displayed, and in the English version, only those in English).
AMD is building the next generation of AI-powered analytics platforms to transform how semiconductor engineers and analysts understand yield, test, and quality data. In this role, you will help design and build multi-agent, LLM-driven systems that assist engineers in investigating complex questions—such as yield loss, defect trends, customer returns, and emerging failure mechanisms. You will work in a highly collaborative environment alongside AI architects, software engineers, product leaders, and semiconductor domain experts. Your focus will be on developing intelligent systems where AI agents can reason over structured data, propose hypotheses, and guide users toward root causes—while maintaining transparency, traceability, and strong human-in-the-loop controls. This role offers the opportunity to work on real, high-impact problems at the intersection of AI, data platforms, and semiconductor manufacturing.
Job Responsibility:
Design and develop multi-agent analytics workflows, enabling specialized AI agents to collaborate on data retrieval, hypothesis generation, root-cause analysis, and insight summarization
Implement agent orchestration logic, including task decomposition, planning, routing, and inter-agent communication
Integrate large language models with structured data sources, analytics engines, and internal APIs using tool and function-calling techniques
Build and manage state, memory, and context handling to support multi-step analytical reasoning
Develop and maintain retrieval-augmented generation (RAG) pipelines over enterprise and domain-specific datasets
Apply guardrails, evaluation strategies, and observability to ensure AI systems are reliable, explainable, and production-ready
Partner closely with domain experts to capture and encode tribal knowledge as reusable AI capabilities
Contribute to shared architectural patterns and agent frameworks used across teams
Requirements:
Strong software engineering fundamentals, including system design, debugging, and API development
Proficiency in Python and experience building backend or data-centric systems
Hands-on experience working with large language models (commercial or open-source)
Comfort working with structured data, such as SQL databases, dataframes, and analytics outputs
Experience with agentic AI frameworks (e.g., LangChain, LangGraph, LlamaIndex)
Familiarity with vector databases and hybrid retrieval approaches
Experience building analytics-heavy or data-intensive products
Exposure to LLM evaluation and testing, including quality and regression assessment
Understanding of distributed systems, asynchronous workflows, or microservices
Experience collaborating with domain experts to translate problem knowledge into software solutions
Bachelor's or Master's degree in Computer Science, Engineering, or related field