AMD

2 weeks ago

GenAI Software Development Architect

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 7 hours agoStatus: Live

Job Summary

Own the end-to-end technical architecture for an AI-native hardware and firmware validation platform. Design multi-agent orchestration and retrieval-augmented knowledge systems (RAG, vector search, hybrid retrieval, reranking, knowledge graphs) and integrate MCP server infrastructure. Partner with validation engineers and hardware teams to translate requirements into production-grade systems, establish engineering standards, and lead reliability practices including observability, automated testing, and unattended execution.

Location: Santa Clara, Austin, Seattle

Workplace: Onsite

Employment Type: Full time

Job Function: Software Engineering

Seniority: Mid level

Key Responsibilities

•Design and own the architecture of an AI-native validation platform where autonomous LLM agents execute hardware and firmware test campaigns end-to-end without a human in the loop.
•Architect retrieval-augmented generation systems including ingestion pipelines, chunking, embedding models, vector stores, knowledge graph backends, hybrid search, and reranking.
•Define multi-agent orchestration patterns (context management, anti-hallucination contracts, tool-use boundaries, inter-agent protocols, and crash recovery) for long-running unattended runs.
•Own MCP integration across the agent layer, knowledge backends (e.g., Qdrant/Neo4j/LightRAG), and external systems (e.g., Slack, Jira, Confluence, GitHub).
•Establish and enforce AI-native engineering standards, lead reliability practices (validation, audit infrastructure, observability, automated testing, CI/CD), and mentor engineers through design reviews.

Pay and Benefits

Salary: USD 210,000 - 360,000 annually

Key Requirements

•Software development experience with at least 4 years in architecture, staff, or principal engineer roles.
•Hands-on experience designing and shipping production AI-native systems including RAG pipelines and multi-agent coordination.
•Strong understanding of LLM behavior in practice, including grounding, hallucination failure modes, prompt engineering, and model/provider differences.
•Proven retrieval systems experience: vector search, embedding models, hybrid retrieval, reranking pipelines, and knowledge-graph-augmented RAG.
•Strong proficiency in modern programming languages such as Python, TypeScript/Node.js, Go, Java, C#, or Rust, and experience operating production-scale services.

Experience:4+ yearsAI-native systemsSemiconductorDatacenterHardware validationAgentic AI

Education:Bachelor's in Computer Science, Electrical Engineering, or related field

Skills:MentorshipWritten communicationStakeholder collaborationEngineering standardsRoot-cause analysis

Tech Stack:PythonTypeScriptNode.jsGoJavaC#RustAWSAzureGCPRAGVector searchEmbedding modelsHybrid retrievalRerankingKnowledge graphsMCPClaude CodeGitHub CopilotCursor

Company Brief

AMD

Designs and produces semiconductor products including CPUs, GPUs, and adaptive SoCs for consumer, enterprise, and embedded markets, competing across PCs, data centers, and gaming industries.

Industry: Electronics Manufacturing

Company Size: Enterprise (1,001+ employees)

Revenue: USD 1B+

Growth: Public Company

Valuation: Public Company (Market Cap in USD)

Funding: IPO / Publicly Listed

Headquarters: Santa Clara, United States

Founded: 1969

Glassdoor: 3.9

Website LinkedIn

Loading job details...

Preparing the role view and application actions.

AMD