DMTS Physical AI SW Stack

Job Title

DMTS Physical AI Software Stack

Role Summary

Senior technical leadership role responsible for defining the architecture and standards for the product's AI software stack. Leads design and delivery of production-grade AI platforms, framework kernels, kernel/operator optimizations, and model-lowering infrastructure for processor-based AI deployments.

Works across hardware and software teams to ensure scalable, cost-efficient deployment of AI workloads on MIPS/RISC-V based platforms and guides engineering teams on long-term roadmap and implementation.

Experience Level

Senior — typically 15+ years in software engineering with at least 5 years focused on AI/ML software for processor subsystems, hardware accelerators, or distributed systems architecture.

Responsibilities

Key responsibilities include setting technical vision, designing platform components, and ensuring runtime and deployment efficiency.

• Architect and deliver production-grade AI platform stack including ONNX/PyTorch kernel support and framework integrations.
• Define and drive technical roadmap, architectural standards, and engineering best practices.
• Oversee workload performance and operator/kernel optimizations for accelerator-backed processors.
• Design model-lowering approaches and toolchains for deployment to RISC-V / MIPS-based platforms.
• Ensure scalable, cost-effective deployment stacks and infrastructure (CI/CD, containerization, orchestration).
• Mentor engineering teams and provide hands-on technical leadership across hardware/software boundaries.

Requirements

Must-have technical skills and experience.

• 15+ years software engineering experience; 5+ years on AI/ML software for processor subsystems, hardware accelerators, or distributed systems.
• Strong practical experience with neural networks and modern architectures (e.g., Vision Transformers, vision-language models).
• Proficiency in Python, Java, and C/C++; experience with architecture-level optimization.
• Experience with infrastructure and tooling: GitHub, Docker, Kubernetes, CI/CD for ML workloads.
• Experience with AI acceleration hardware and performance tuning for accelerated inference/compute.
• Proven track record in designing and delivering production software platforms and mentoring engineering teams.

Nice-to-have:

• Experience with model lowering toolchains, graph simulators, kernel-level optimizations for RISCV/MIPS platforms.
• Background in low-level runtime/kernel development or compiler flow for accelerators.

Education Requirements

Not specified.

About the Company

Company: GlobalFoundries

Headquarters: Saratoga Springs, New York, USA

GlobalFoundries is a leading contract manufacturer for the global semiconductor industry, with facilities in multiple countries, including the USA. The company develops a broad portfolio of semiconductor technologies and employs around 13,000 people worldwide. GlobalFoundries focuses on enhancing competitiveness in specialized application solutions and fostering innovation in mobile communications, consumer electronics, and automotive applications.