Director, System Software Engineering - Metropolis Accelerated and Inferencing Software

Details

NVIDIA is seeking a hands-on Director of Systems Engineering to lead software and data teams developing GPU-accelerated video intelligence systems for Physical AI. The role covers the full lifecycle from model onboarding to production deployment, using platforms such as DeepStream and VSS. The successful candidate will have deep learning expertise, strong familiarity with modern architectures including transformers, diffusion models, and vision-language models, and experience optimizing inference on NVIDIA GPUs and SoCs.

Responsibilities

• Lead, encourage, and develop engineering and data teams distributed across Europe, Asia, and the United States.
• Architect and operationalize NVIDIA's end-to-end data inference acceleration strategy, supporting inference and continuous performance improvements.
• Drive implementations of TensorRT, vLLM, and other accelerated inference frameworks for edge and enterprise devices.
• Lead accelerated computing efforts for key Metropolis verticals, establish Proofs of Readiness, and guide their implementation.
• Collaborate with Metropolis OEMs and partners to architect optimized custom deep learning models and inference pipelines.
• Provide direct customer support, including debugging, technical education, and handling technical inquiries from Metropolis partners and customers.
• Draft and finalize statements of work with internal customers and partners.
• Orchestrate performance benchmarking efforts, including achieving leading results on MLPerf across edge and enterprise devices.
• Act as a technical leader for deep learning across multiple teams and use customer insights to influence the design of future SoC and GPU deep-learning hardware.
• Hire strategically, mentor existing teams, and adapt team structures to meet new deep learning challenges.
• Represent NVIDIA deep learning solutions at webinars, conferences, and partner events.

Requirements

• Bachelor's and/or master's degree in Computer Science, Electrical Engineering, or equivalent experience.
• 15+ years of overall experience, including at least 10 years of meaningful involvement in machine learning or deep learning research or practical applications, and 7+ years of leadership experience.
• More than 10 years of industry experience in embedded software, including technical leadership roles accountable for delivering production software in complex environments.
• Deep knowledge of GPU, CPU, and dedicated deep learning architecture fundamentals.
• Experience with low-level performance optimization using heterogeneous computing, including GPU kernels, memory, latency, and efficiency trade-offs.
• Hands-on experience with VLMs, LLMs, or multimodal AI systems applied to perception, data triage, or automated labeling.
• Strong expertise in large-scale data processing, systems building, or machine learning pipelines.
• Strong communication, planning, and technical leadership capabilities.

Preferred Qualifications

• PhD in a relevant field such as Spatial Computing and Awareness, Sim-to-Real Transfer, or Human-to-Physical AI Interaction.
• Deep experience with computer vision, LLMs, VLMs, generative AI models, and relevant standards.
• Technical thought leadership in production deployment of Smart Spaces and Physical AI, with an understanding of sensing, computing, and model architecture constraints and developments.
• Current experience leading global teams across multiple continents and time zones.

Benefits

• Competitive salary and a generous benefits package.
• Eligibility for equity and NVIDIA benefits.
• NVIDIA is an equal opportunity employer committed to an inclusive work environment.