GenAI Software Development Engineer

Overview In this role you will help build an AI-native platform that runs autonomous hardware validation at scale, shaping multi-agent orchestration, RAG pipelines, and knowledge management. You’ll work within Global Cluster Engineering to empower distributed infrastructure used by hardware and firmware teams. You’ll tackle complex problems around grounding, evaluation, and reliability in automated environments. This is a high-impact opportunity to advance AI-native tooling that accelerates validation workflows and knowledge sharing. Responsibilities Design and maintain the AI agent orchestration layer, including multi-agent dispatch, context management, guardrails against hallucinations, progress tracking, crash recovery, and inter-agent communication protocols Develop and improve the retrieval-augmented generation pipeline with document ingestion from Slack, Git Hub, Jira, Confluence; implement chunking, embedding, hybrid search, reranking; index knowledge graphs via LightRAG + Neo 4jBuild intuitive web applications and developer experiences to interact with AI agents, validation workflows, dashboards, and tooling (React/Next.js/Angular/Vue)Design distributed services, APIs, event-driven architectures, and microservices powering AI workflows and platform integrations Create scalable AI services for metadata generation, feature extraction, and knowledge retrieval with grounded context at query time Develop LLM-powered tooling for automated test plan generation, quality auditing, failure triage, autonomous knowledge curation, and report generation Deploy agentic AI solutions—autonomous agents, orchestration frameworks, and LLM-powered workflows that transform validation operations Collaborate with validation engineers and hardware teams to translate domain requirements into flexible software solutions Ensure AI/ML systems meet security standards and data privacy requirements across LLM integrations and credentials-handling systems Own features end-to-end from estimation and design review to coding, deployment, and post-launch measurement Maintain resilient systems with observability, automated testing, monitoring, CI/CD via IaC (Terraform); participate in on-call and root-cause analysis Write clean, well-tested code that ensures reliability for other engineers and agents Onboard new product teams to the platform and translate domain knowledge into agent capabilities Key requirements Production software development experience with a portfolio of systems Experience shipping real LLM-powered systems and focus on grounding, evaluation, and failure modes Hands-on experience building RAG pipelines (embedding models, vector databases, chunking, retrieval evaluation, hybrid search, reranking)LLM engineering experience (tool use, multi-agent orchestration, prompt engineering, context management, hallucination mitigation)Proficiency in Python, Type Script/Node.js, Go, Java, C#, or Rust; Python preferred Experience with async programming, APIs, distributed systems, and reliable unattended deployments Cloud infrastructure experience (AWS/Azure/GCP) with provisioning and scalable production workloads Experience with AI tooling and developer tools (Claude Code, Git Hub Copilot, Cursor)Familiarity with knowledge graphs or graph-augmented RAG (Neo 4j, LightRAG)Exposure to security/compliance considerations in AI/ML systemsCI/CD and automated test infrastructure; API design; observability and monitoring On-call experience and bias toward reliability Academic credentials: BS or MS in CS, Electrical Engineering, or related field Collaborative Curious and proactive problem-solver Strong communication with cross-functional teams Python Type Script/Node.js Go