Director, System Software Engineering - Metropolis Accelerated And Inferencing Software

Details

Within NVIDIA's Edge AI, Metropolis, and Blueprints (EMB), this team powers NVIDIA’s Vision AI strategy from model onboarding to production deployment. We transform foundation models into real-time, GPU-accelerated video intelligence systems using Deep Stream and VSS. Our focus includes scaling multimodal reasoning and enabling agentic development workflows. We connect production data with model improvement. This work positions NVIDIA as the default platform for Physical AI.

The Metropolis team within EMB is looking for a Director of Systems Software Engineering who combines visionary leadership with deep technical execution. This high-impact, hybrid role is designed for a leader who not only manages remotely but also models code, masters low-latency inference, and understands modern architectures such as transformers, diffusion models, and VLMs. If you are an industry expert who thrives on tuning NVIDIA GPUs/SoCs and translating accelerated computing pipelines into measurable, real-world Enterprise and Edge solutions, let’s talk.

Responsibilities

• Global Team Leadership & Scaling: Direct, mentor, and strategically grow a decentralized, world-class engineering and data team across Europe, Asia, and the US, with a focus on next-generation deep learning challenges.
• Inference Strategy & Architecture: Own NVIDIA’s end-to-end Vision AI Acceleration strategy, driving TensorRT, vLLM, and accelerated frameworks to deliver low-latency performance improvements across Edge and Enterprise devices.
• Partner Collaboration & Go-to-Market: Architect highly optimized deep learning pipelines for major Metropolis OEMs and partners, define Proofs of Readiness (PORs), finalize SOWs, and provide technical debugging and education when needed.
• Multi-functional Leadership for Deep Learning: Develop upcoming SoC/GPU hardware using customer insights and represent NVIDIA’s vision globally.
• Performance Benchmarking: Drive continuous optimization efforts to secure industry-leading results on benchmarks like MLPerf across diverse platforms.

Requirements

• Deep Expertise & Pedigree: A Bachelor’s or Master’s in CS/EE (or equivalent experience) backed by 15+ years in engineering, including 10+ years in deep learning research/practice, 7+ years in leadership, and 10+ years delivering production-grade embedded software in complex environments.
• Low-Level Hardware Intuition: Strong understanding of CPU, GPU, and dedicated deep learning architectures, with a track record of extracting maximum performance through heterogeneous computing and low-level optimizations (kernels, memory, latency).
• Modern AI Fluency: Hands-on experience building large-scale data pipelines and deploying LLMs, VLMs, or multimodal AI systems for perception, data triage, or automated labeling.
• Operational Excellence: Strong communication and clear project planning skills needed to guide multi-functional technical initiatives with outstanding precision.

Benefits

• Competitive salaries and a generous benefits package.
• You will also be eligible for equity and benefits.