Software QA Automation Lead, AI Systems (SuperAgent Team)

At Cadence, we hire and develop leaders and innovators who want to make an impact on the world of technology.

Cadence is a pivotal leader in electronic design, building upon more than 30 years of computational software expertise. We apply our Intelligent System Design strategy to deliver software, hardware, and IP that turn design concepts into reality.

This strategy is supplemented by AI-augmented development practices throughout all our organizations to empower our team to focus on creative problem-solving and innovation. Our customers are the world's most innovative companies, delivering extraordinary electronic products-from chips to boards to systems-for dynamic market applications including consumer, hyperscale computing, 5G communications, automotive, aerospace, industrial, and health. Join us and be part of a culture that values innovation, collaboration, and customer success.

At Cadence, we hire and develop leaders and innovators who want to make an impact on the world of technology.

Job Title: Software QA Automation Lead, AI Systems (SuperAgent Team)

Location: Cork, Ireland

Reports to: Software Engineering Director

Job Overview:

Chips are at the center of today's tech-driven world. But as their complexity and specialization skyrocket due to AI, the manual orchestration of EDA tools is no longer sustainable. At Cadence, we are building the ChipStack AI Super Agent-the industry's first agentic AI workflow for front-end silicon design and verification.

Our "virtual engineers" understand specifications, write testbenches, run simulations, and iterate on fixes autonomously. In an industry where a single bug can cost millions in a re-tapeout, the reliability of our AI agents is paramount. We are looking for a visionary QA Automation Lead to define how autonomous agentic systems are tested, evaluated, and deployed at scale.

This is a high-impact leadership role within the ChipStack SuperAgent Team. You will be responsible for the end-to-end quality strategy of our AI agent ecosystem. Testing an agent is fundamentally different from testing traditional software; you will be architecting frameworks that evaluate non-deterministic reasoning, multi-tool orchestration (Xcelium, Jasper, JedAI), and "Mental Model" grounding.

The ideal candidate is a strong full-stack engineer who understands the nuances of both cloud-scale SaaS and secure, on-premise semiconductor environments. You will lead the transition from manual validation to a sophisticated, AI-augmented automated evaluation system.

Job Responsibilities:

• Lead QA Strategy: Design and execute a comprehensive automation roadmap for agentic AI systems, focusing on reliability, safety, and performance across the semiconductor design lifecycle.
• Architect Evaluation Frameworks: Build "LLM-native" automated testing suites to benchmark agent reasoning, planning, and self-correction loops.
• Full-Stack Automation: Develop robust test infrastructure using Python (for core logic/agent interaction) and TypeScript (for UI/UX and integration layers).
• Hybrid Environment Validation: Ensure seamless performance and security across modern Cloud (AWS/Azure) and air-gapped On-Premise deployments.
• Observability & Monitoring: Implement advanced logging and tracing to detect agent "drift" and hallucinations in production-grade EDA workflows.
• Collaborative Leadership: Work closely with ML scientists and software engineers to integrate continuous evaluation into the CI/CD pipeline.

• Experience: 8+ years in Software QA/Automation, with at least 2+ years in a lead or architect capacity.
• Technical Proficiency: Expert-level Python and TypeScript. You should be comfortable building complex automation frameworks from the ground up.
• Infrastructure Knowledge: Deep experience with Cloud-native architectures (Kubernetes, Docker) and a solid understanding of the constraints of on-premise enterprise environments.
• QA Fundamentals: Mastery of system-level testing, regression testing for distributed systems, and performance/load testing.
• Education: BS/MS/PhD in Computer Science, Computer Engineering, or a related technical field.

• Agentic AI Testing: Experience testing frameworks like LangGraph, CrewAI, or LangChain. Familiarity with evaluating ReAct patterns and tool-calling reliability.
• RAG & Data Evaluation: Understanding of how to validate RAG pipelines, including retrieval accuracy, grounding techniques, and context-engineering effectiveness.
• AI-Assisted QA: Interest in using AI tools to generate test cases, analyze failure logs, and predict potential regressions in silicon design artifacts.
• EDA Awareness: A passion for semiconductor verification and an interest in how AI can solve the "verification bottleneck" in chip design.

• Challenge the Status Quo: We don't just follow industry standards; we set them for the next era of AI-driven silicon.
• Strong Opinions, Loosely Held: We value technical rigor and data-driven debate. We pivot quickly when the data proves us wrong.
• Ship Fast, Ship Quality: In EDA, "shipping quality" is the only option. We build at lightning speed without ever compromising the high standards of the semiconductor industry.
• Proud of Our Craft: We take pride in the reliability of our systems, knowing they power the world's most advanced chips.

• Competitive salary
• 25 days holiday per year
• Private Medical and Dental plans, Income Protection and Life Insurance
• Group Personal Pension Plan
• Cycle to work scheme and gym subsidy
• 5 days paid time to volunteer to give back to our communities
• Employee Stock Purchase Plan
• The opportunity to work for a Great Place to Work© & Fortune 100 organization