Senior GenAI Platform Engineer: LLM & RAG Orchestration

Advanced Micro Devices; Santa Clara (CA); On-site; USD 140,000 - 210,000; Full time

Job summary

Advanced Micro Devices is seeking two Senior Software Engineers to design AI-native platforms that orchestrate autonomous agents for hardware validation campaigns. You will build multi-agent systems, RAG pipelines, and developer tools to enable scalable knowledge sharing and reliability.

You will work across backend, frontend, and AI services, collaborating with validation and hardware teams to deliver robust, observable systems at global scale. Santa Clara location preferred.

Qualifications

• Production-grade software engineering experience.
• Strong AI-native development track record.
• Experience with RAG pipelines and vector databases.
• Comfort with multi-agent orchestration and tool-use frameworks.
• Knowledge of software reliability and observability.

Responsibilities

• Design, build, and maintain multi-agent orchestration layer.
• Develop RAG pipelines with embedding strategies and hybrid search.
• Create developer UX for interacting with AI agents and dashboards.
• Build distributed backend services powering AI workflows.
• Develop scalable AI services for metadata and knowledge retrieval.
• Create LLM-powered tooling for testing, auditing, and reporting.
• Deploy agentic AI solutions across hardware teams.
• Collaborate with validation and hardware teams to translate needs.

Skills

Python

TypeScript/Node.js

Go

Java

C#

Rust

LLM Tooling

Distributed Systems

Async Programming

Observability

Education

BS or MS in CS/EE or related

Tools

Neo4j

LightRAG

Slack API

GitHub API

Jira/Confluence APIs

Terraform

Jira

Confluence

React/Next.js

Job description

Advanced Micro Devices is seeking two Senior Software Engineers to design AI-native platforms that orchestrate autonomous agents for hardware validation campaigns. You will build multi-agent systems, RAG pipelines, and developer tools to enable scalable knowledge sharing and reliability.

You will work across backend, frontend, and AI services, collaborating with validation and hardware teams to deliver robust, observable systems at global scale. Santa Clara location preferred.