AI Systems Architect Models and Hardware Co Design

You will evaluate modern AI model architectures, training and inference characteristics, and workload requirements. You will translate model requirements into efficient hardware implementations, develop performance models, optimize models and dataflows, and support efficient deployment on new compute platforms.

Responsibilities

• Analyze modern AI model architectures and their computational and system requirements
• Evaluate model suitability for application domains and workloads
• Translate model requirements into efficient silicon implementations
• Identify model, algorithm, and dataflow optimizations for hardware performance and scalability
• Assess training and inference pipelines for hardware-design implications
• Develop performance and efficiency models for architectural decisions
• Support efficient model deployment on new compute platforms
• Identify emerging model architectures that may benefit from specialized hardware

Requirements

• Machine learning architecture
• Transformer
• Machine learning mathematics
• Optimization
• Deep learning
• PyTorch
• JAX
• TensorFlow
• Computation graph
• Dataflow
• Model training
• Model inference
• Systems thinking

Benefits

• Equity compensation
• Medical coverage
• Dental coverage
• Vision coverage
• Paid time off
• Flexible work arrangements