DMTS Physical AI SW Stack
GlobalFoundries2 months ago
Bengaluru, IndiaStaff+
Responsibilities
- Lead the technical vision and architectural standards for the product’s AI software stack.
- Architect and deploy production-grade AI platforms for MIPS AI platforms using ONNX, PyTorch, and other framework kernels.
- Oversee workload performance, operator and kernel optimization, deployment-stack optimization, and cost-efficient scalability.
- Define model-lowering architecture and frameworks for transferring models to RISC-V-based MIPS platforms.
- Develop graph simulators and optimize infrastructure and applications across the AI software stack.
- Define the long-term technical roadmap and mentor engineering teams.
Requirements
- 15+ years of software engineering experience.
- 5+ years focused on AI/ML software for processor subsystems, hardware accelerators, and distributed systems architecture.
- Deep hands-on experience with neural networks, Vision Transformers, and Vision Language Action Models.
- Strong experience with Python, Java, C, C++, and architecture-level optimization.
- Hands-on experience with GitHub, Docker, Kubernetes, and AI acceleration hardware.
Benefits
- GlobalFoundries offers a multicultural and inclusive workplace and is an equal opportunity and affirmative action employer.
- Employment offers are subject to successful background checks, applicable medical screenings, and local laws and regulations.
- Benefits information is provided at https://gf.com/about-us/careers/opportunities-asia.
Categories
About GlobalFoundries
GlobalFoundries manufactures semiconductors as a contract foundry, offering process technologies, design enablement, and wafer fabrication for chip designers and device makers across automotive, data center, mobile, and IoT markets. Headquartered in Malta, New York and founded in 2009, it operates fabs in the U.S., Europe, and Asia and is listed on Nasdaq (GFS). Customers use its analog/RF, high-voltage, and specialty nodes alongside advanced CMOS.