Applied AI Engineer - Silicon Co-Design Group
Core
Architecting and implementing AI/LLM-powered systems to enhance efficiency, scalability, and intelligence in semiconductor validation, automation, and workflow infrastructure.
Role type
Applied AI Engineer (Silicon Co-Design)
Builds
AI-driven toolchains for CPU, GPU, and Tegra SoC design and validation
Domain
Semiconductor hardware design and validation
Deliverable
production ML models
Required skills
Python, C/C++/C#/Java/Scala, deep learning frameworks (PyTorch/TensorFlow), agentic/orchestration tools (NeMo, LangChain, Semantic Kernel, AutoGen, CrewAI, n8n), scalable AI/ML model deployment, debugging, computer architecture, high-speed interfaces, timing, power basics, firmware/driver structures, hardware interaction
Preferred skills
LLM crafting and launch, orchestration agents managing hundreds/thousands of tools, silicon bring-up, characterization, lab debug (oscilloscopes, multimeters, logic analyzers), chip/system characterization, HW/SW interaction debugging
Technologies
PyTorch, TensorFlow, NeMo Agent Toolkit, LangChain, Semantic Kernel, AutoGen, CrewAI, n8n
Responsibilities
Designing and implementing AI/LLM-powered systems for post-silicon validation and automation; Collaborating with multi-functional teams for AI integration and performance optimization; Evaluating emerging frameworks and tools for AI efficiency; Establishing data-driven indicators to quantify AI impact and drive continuous improvement
Seniority
Mid-to-Senior, hands-on IC
