Director, System Software Engineering - Metropolis Accelerated and Inferencing Software

Tasks

• Apply customer insights to shape SOC GPU deep learning hardware
• Architect and operationalize end to end data inference acceleration strategy
• Collaborate with OEMs and partners on accelerated deep learning model pipelines
• Debug and provide technical education to customers
• Draft and finalize statements of work
• Drive TensorRT VLLM and accelerated framework implementations for inference
• Lead and develop engineering and data teams
• Orchestrate performance benchmarking on MLPerf
• Provide technical leadership across deep learning teams
• Represent deep learning solutions at webinars and conferences
• Set up proofs of readiness and guide implementations
• Strategically hire and mentor teams

Perks/Benefits

• Comprehensive benefits
• Equity

Skills/Tech-stack

CPU | Continuous Performance Improvement | Data Processing | Deep learning | Deep learning inference | Diffusion Models | Edge Computing | Embedded Software | GPU | Heterogeneous computing | Inference Optimization | Kernels | Language Models | Large Language Models | Low-level performance | Low-level performance optimization | MLPerf | Machine Learning | Machine Learning Pipelines | Memory latency | Multimodal AI | Performance improvement | Performance optimization | TensorRT | Transformers | VLLM | Vision Language Models | Vision-language