Manager Software Development

Advanced Micro Devices, Inc•Santa Clara, CA

11d

About The Position

AMD is hiring for a role in its Global Cluster Engineering organization to build a platform where autonomous AI agents run hardware validation campaigns, triage failures, and grow a shared knowledge base. The position focuses on designing and developing an LLM agent framework, retrieval-augmented generation (RAG) pipelines, an MCP backend, and developer tooling for distributed infrastructure at global scale. The work is AI-native, involving multi-agent orchestration, tool-use frameworks, and knowledge graph integrations. Deep hardware expertise is not required, though curiosity about firmware validation and network hardware is useful. AMD states it is hiring two Senior Software Engineers for this role, with specific areas of ownership shaped by each person's strengths and interests. The role includes technical and engineering leadership: leading and growing engineering teams, hiring and mentoring, setting technical direction, and delivering multi-workstream projects. The successful candidate will build production AI systems and services, work with validation and hardware teams, and own features from estimation and architecture through deployment and post-launch measurement. The posting requires a BS or MS in Computer Science, Electrical Engineering, or a related field. The role is not eligible for visa sponsorship or transfer.

Requirements

Software development experience and a strong portfolio of production systems.
Experience leading and growing engineering teams, including hiring, mentoring, developing engineers, setting technical direction, and delivering multi-workstream projects.
Hands-on experience building RAG pipelines, including embedding models, vector databases, chunking, retrieval evaluation, hybrid search, and reranking.
Production experience with LLM tool use, multi-agent orchestration, prompt engineering, context management, and hallucination mitigation.
Strong proficiency in at least one modern programming language, such as Python, TypeScript/Node.js, Go, Java, C#, or Rust, and demonstrated ability to build and operate production-scale services.
Experience with async programming, API design, distributed systems, and clean code practices.
Experience designing reliable automated or unattended systems, including crash recovery, audit trails, state management, and observability.
Experience with AWS, Azure, or GCP, including infrastructure provisioning, managed services, networking, and production deployments at scale.
Active use of AI coding assistants and LLM-powered developer tools.
BS or MS degree in Computer Science, Electrical Engineering, or a related field.

Nice To Haves

Python experience, given its use in the AI/ML ecosystem.
Experience building modern web applications with React, Next.js, Angular, Vue, or similar frameworks.
Experience with Model Context Protocol (MCP) or agentic platforms such as Claude Code, LangGraph, CrewAI, or AutoGen.
Familiarity with knowledge graph systems such as Neo4j or LightRAG, or graph-augmented RAG.
Background in the semiconductor, datacenter, or networking industry, or high-level understanding of hardware validation or firmware development.
Experience with CI/CD systems and automated test infrastructure.
Exposure to Slack API, GitHub API, or Atlassian REST APIs.
Experience with data pipeline design, ETL workflows, data warehousing, or analytics platforms.

Responsibilities

Design, build, and maintain an AI agent orchestration layer, including multi-agent dispatch, context management, hallucination safeguards, progress tracking, crash recovery, audit trails, and inter-agent communication.
Build and improve RAG pipelines, including ingestion from Slack, GitHub, Jira, and Confluence; chunking and embedding; hybrid search; reranking; and knowledge graph indexing with LightRAG and Neo4j.
Build web applications and developer experiences for interacting with AI agents, knowledge systems, validation workflows, observability dashboards, and operational tooling.
Design and implement distributed services, APIs, event-driven architectures, and microservices for AI workflows and platform integrations.
Develop scalable, low-latency AI services for metadata generation, feature extraction, and knowledge retrieval.
Build LLM-powered developer tools for test plan generation, test case quality auditing, failure triage, knowledge curation, and report generation.
Develop and deploy autonomous agents, multi-agent orchestration frameworks, and LLM-powered workflows for hardware validation operations.
Collaborate with validation engineers, hardware teams, and engineering peers to turn business and domain requirements into software solutions.
Ensure AI/ML systems meet security standards and protect data across LLM integrations, RAG pipelines, and credential-handling systems.
Own features end-to-end, from project estimation and architecture review through coding, deployment, and post-launch measurement.
Build resilient systems with observability; implement automated testing, monitoring, and CI/CD pipelines using infrastructure-as-code tools such as Terraform.
Participate in on-call rotations, conduct root-cause analysis, and improve reliability.
Write clean, well-tested, maintainable code.
Work with validation engineers to translate domain knowledge into agent skills and onboard new product teams onto the platform.
Lead and grow engineering teams, hire and mentor engineers, set technical direction, and manage delivery across multi-workstream projects.