Infrastructure AI/ML Engineer for Memory Design, Characterization, and Yield Optimization

Job Title

Infrastructure AI/ML Engineer for Memory Design, Characterization, and Yield Optimization

Role Summary

Lead design and deployment of agentic AI infrastructure and multi-agent workflows to accelerate memory design, characterization, silicon bring-up, and yield optimization within the Central Engineering Group. Collaborate with memory designers, DFT experts, EDA tool specialists, and infrastructure engineers to integrate LLM-driven pipelines with EDA suites and enterprise data sources.

Experience Level

Senior - 15+ years of progressive, relevant experience in memory design, DFT, silicon yield analysis, software architecture, and AI systems engineering.

Responsibilities

Drive architecture, implementation, and scaling of production AI workflows that support memory engineering and manufacturing outcomes.

• Architect, deploy, and scale distributed multi-agent AI frameworks tailored to memory design, PPA optimization, DFT, and yield.
• Orchestrate long-horizon autonomous agent executions for multi-step reasoning, task decomposition, and decision-making across design, silicon bring-up, and yield analysis.
• Integrate LLM-driven agent pipelines with EDA tools, custom in-house tools, and enterprise data repositories.
• Develop ML models and pipelines to automate classification and debugging of scan failures and correlate failures with DFT structures.
• Build predictive yield models that combine fab process parameters, PCM, and E-test data to identify yield excursions early.
• Partner with Memory Design Leads, EDA Tool Specialists, and Infrastructure Engineers to convert hardware engineering processes into modular agentic workflows aligned to technical milestones.

Requirements

Must-have technical skills, tools, and experience.

Must-have:

• 15+ years of relevant experience in memory design, DFT, silicon yield analysis, software architecture, and AI systems engineering.
• Experience designing and characterizing embedded memory in advanced process nodes and familiarity with silicon bring-up and yield analysis.
• Proven experience architecting production-grade LLM applications: multi-agent orchestration, function-calling/tool-use, and retrieval-augmented generation (RAG).
• Experience integrating agentic systems with enterprise tools and knowledge sources, including building/consuming MCP servers and packaging agent capabilities.
• Hands-on familiarity with EDA tooling and verification environments (Synopsys, Cadence, Siemens EDA, SystemVerilog, UVM).
• Strong software and infrastructure skills: Python, TCL, microservices, REST APIs, Docker, Kubernetes, sandboxing, and config-driven workflow engines.
• Experience with evaluation metrics, testing benchmarks, and safety guardrails for non-deterministic AI systems in high-stakes environments.
• Technical knowledge of vector databases and cloud-native containerized orchestration pipelines.

Nice-to-have:

• Experience with compute-in-memory design and architecture.
• Familiarity with agent orchestration frameworks such as LangGraph.

Education Requirements

Master's degree or Ph.D. in Electrical Engineering or Computer Engineering.

About the Company

Company: Broadcom

Headquarters: Irvine, California, United States

Broadcom is a global technology leader that designs, develops, and supplies a wide range of semiconductor and infrastructure software solutions. The company is known for its innovations in wireless and broadband communications, enabling a connected world.