System Architect Bardi

System Architect
Bardi
Emilia Romagna, Bardi

System Architect - Milan or Florence I am looking for an experienced professional to play a key role in designing and optimising advanced hardware architectures for next-generation AI platforms. This is an exciting opportunity to work at the forefront of innovation, contributing to the development of high-performance AI accelerators. As a System Architect , you will focus on memory design, intra- and inter-chip networking, system integration, and performance tuning. You will collaborate closely with cross-functional teams to define and implement architectures that maximise efficiency and scalability. Your expertise will be instrumental in shaping the future of AI processing. Key Responsibilities: Design and optimise next-generation AI accelerators, focusing on memory and network architectures. Develop architectural models, validate their performance across AI workloads, and define optimal configurations. Create detailed architectural specifications and implement advanced hardware prototypes. Conduct rigorous performance evaluation tests for architectural verification. Work closely with software engineers, digital designers, and ML scientists to align system architecture with project goals. Communicate complex technical concepts effectively to both technical and non-technical stakeholders. Contribute to research initiatives, publications, and intellectual property development. Required Skills and Experience: Master's or PhD in Computer Science, Electrical Engineering, or a related field with a focus on circuit design, computer architecture, or high-performance computing. Strong experience in hardware and system architecture, including memory management, dataflow, and networking infrastructure. Proficiency in software and hardware development, with strong programming skills in Python. Basic knowledge of neural networks, particularly Convolutional or Transformer-based models for AI applications. Experience or knowledge of networking protocols such as RoCE or Infiniband, and (Remote) Direct Memory Access is highly desirable Understanding common computer architectures, including CPUs, GPUs, and AI accelerators is highly desirable Proven track record of contributions to AI/ML Email - jordan. browneic-resources.com Tel - 01189073075 LinkedIn - https://www.linkedin.com/in/jordan-browne-b4a08b20b/