AI-Native SDE: Multi-Agent RAG & Orchestration

AMD; Santa Clara (CA); On-site; USD 150,000 - 210,000; Full time

Job summary

AMD is building an AI-native platform where autonomous agents manage hardware validation campaigns, triage failures, and grow a shared knowledge base. You will design the LLM agent framework, RAG pipelines, MCP backend, and developer tooling to power distributed infrastructure at global scale.

This Senior Software Engineer role sits in Global Cluster Engineering, focusing on multi-agent orchestration, knowledge graphs, and scalable AI services.

Qualifications

• BS or MS degree in Computer Science, Electrical Engineering, or related field.
• Experience building production-scale services and distributed systems.
• Strong background in AI-native software and LLM-powered tooling.

Responsibilities

• Design, build, and maintain multi-agent orchestration layers for AI agents.
• Develop RAG pipelines with embedding, vector stores, and retrieval evaluation.
• Create developer experiences and web UIs for interacting with AI agents and validation workflows.
• Design distributed services, APIs, and event-driven architectures powering AI workflows.
• Ensure security, reliability, and observability across AI/ML software stacks.

Skills

Python

TypeScript/Node.js

Go

Java

C#

Rust

Async programming

API design

Distributed systems

Observability

Cloud platforms

LLM tooling

Education

BS or MS in Computer Science or related field

Tools

Neo4j

LightRAG

Jira

Confluence

Slack API

GitHub API

Job description

AMD is building an AI-native platform where autonomous agents manage hardware validation campaigns, triage failures, and grow a shared knowledge base. You will design the LLM agent framework, RAG pipelines, MCP backend, and developer tooling to power distributed infrastructure at global scale.

This Senior Software Engineer role sits in Global Cluster Engineering, focusing on multi-agent orchestration, knowledge graphs, and scalable AI services.