Responsibilities
THE ROLE:
We are building a platform where autonomous AI agents run hardware validation campaigns, triage failures, and continuously grow a shared knowledge base — without a human in the loop. You will be a core engineer on this system, designing and building the LLM agent framework, RAG pipelines, MCP backend, and developer tooling that make it work. This role sits within the Global Cluster Engineering organization, where you will develop software that powers distributed infrastructure at global scale.
This is an AI-native software engineering role: you will spend your time building multi-agent orchestration systems, retrieval-augmented generation pipelines, tool-use frameworks, and knowledge graph integrations. You do not need deep hardware domain knowledge — but intellectual curiosity about how firmware validation and network hardware works will help you build better tools for the engineers who do.
We are hiring two Senior Software Engineers into this role; specific areas of ownership will be shaped by each person's strengths and interests.
THE PERSON:
Experience:
software development experience, with a strong portfolio of production systems
AI-Native Development:
Genuine passion for building AI-native software — you follow the field, have shipped real LLM-powered systems, and care about getting the details right (grounding, evaluation, failure modes, not just prompts)
RAG Systems:
Hands-on experience building RAG pipelines — embedding models, vector databases, chunking strategies, retrieval evaluation, hybrid search, and reranking
LLM Engineering:
Production experience with LLM tool use, multi-agent orchestration, prompt engineering, context management, and hallucination mitigation
Core Skills:
Strong proficiency in one or more modern programming languages such as Python, TypeScript/Node.js, Go, Java, C#, or Rust, with demonstrated ability to build and operate production-scale services. Python experience is preferred due to the AI/ML ecosystem
Engineering excellence:
Async programming, API design, distributed systems, clean code practices. Experience designing for reliability in automated/unattended environments — crash recovery, audit trails, state management, observability
Cloud Infrastructure:
Experience with AWS, Azure, or GCP — infrastructure provisioning, managed services, networking, and deploying production workloads at scale
AI Tooling:
Active use of AI coding assistants and LLM-powered developer tools (Claude Code, GitHub Copilot, Cursor, etc.) to accelerate development and problem-solving
KEY RESPONSIBILITIES:
- Agent Orchestration: Design, build, and maintain the AI agent orchestration layer — multi-agent dispatch, context window management, anti-hallucination guardrails, progress tracking, crash recovery, audit trails, and inter-agent communication protocols
- RAG Pipeline Development: Build and continuously improve the retrieval-augmented generation pipeline — document ingestion from Slack, GitHub, Jira, and Confluence; chunking and embedding strategies; hybrid vector + keyword search; cross-encoder and LLM-based reranking; knowledge graph indexing via LightRAG + Neo4j
- Developer Experience & User Interfaces
- : Build intuitive web applications and developer experiences enabling engineers to interact with AI agents, knowledge systems, validation workflows, observability dashboards, and operational tooling. Experience building modern web applications using React, Next.js, Angular, Vue, or similar frameworks.
- Backend Systems: Design and implement distributed services, APIs, event-driven architectures, and microservices powering AI workflows and platform integrations.
- AI Services: Design and implement scalable, low-latency AI services powering metadata generation, feature extraction, and knowledge retrieval — ensuring agents have accurate, grounded context at query time
- LLM-Powered Tooling: Build LLM-powered developer tooling — automated test plan generation, test case quality auditing, AI-driven failure triage, autonomous knowledge curation after every test run, and intelligent report generation
- Agentic AI Deployment: Develop and deploy agentic AI solutions — autonomous agents, multi-agent orchestration frameworks, and LLM-powered workflows — that transform validation operations across hardware teams
- Stakeholder Collaboration: Work closely with validation engineers, hardware teams, and engineering peers to translate business and domain requirements into flexible, well-designed software solutions
- Security & Compliance: Ensure AI/ML systems comply with security standards and best practices, addressing data privacy and protection concerns across all LLM integrations, RAG pipelines, and credential-handling systems
- End-to-End Ownership: Own features end-to-end — from project estimation and architecture review through coding, deployment, and post-launch measurement
- Operational Excellence: Build resilient systems with strong observability; implement automated testing, monitoring, and CI/CD pipelines using infrastructure-as-code tools (Terraform); participate in on-call rotations and drive root-cause analysis and reliability improvements
- Code Quality: Write clean, well-tested, maintainable code — other engineers and agents depend on what you build; quality directly affects system reliability
- Onboarding: Collaborate with validation engineers to translate domain knowledge into agent skills and onboard new product teams onto the platform
Qualifications
