Principal Product Manager, GPUs and AI Accelerators

Code Metal is redefining code translation for mission-critical industries. We build code-to-code translation platforms that help commercial and defense partners across AI, advanced signal processing and HPC move quickly and reliably from algorithm to silicon. Our platform accelerates deployment of performance-critical AI and Signal-Processing workloads to a host of compute platforms including GPUs and domain specific accelerator ASICs. 

We are hiring a Principal-level Technical Product Manager for GPUs and AI Accelerators, who will be a critical part of defining a new programmability paradigm for our customers who build GPUs and AI Accelerators.

The Role

This is a leadership role that exists to produce a clear outcome:

Code Metal has a clear product roadmap for supporting accelerated development and deployment of AI, Image Processing and Signal Processing applications on the most commonly used GPUs (edge or data-center) and AI accelerator hardware. 

You will work directly with customers, engineers, and growth leaders to identify source languages, target languages and hardware target platforms for applying Code Metal’s verified code translation technology.

Success is measured by clarity, and time-to-impact.

Responsibilities:

• Own product strategy and roadmap for code translation pipelines focused on programmability of GPUs and AI accelerator platforms. 
• Define and prioritize the GPUs and variants (NPU, Vector-Processors, IPU, AI accelerators) to target for accelerated deployment
• Engage directly with commercial and defense customers to understand how they evaluate, adopt, accredit, and scale new technology
• Combine customer and end-user needs with technical feasibility to shape functional specifications, user stories, and success metrics
• Identify patterns across customer engagements that inform platform capabilities rather than one-off solutions

• 5 years of experience in product management, technical product leadership, or adjacent roles in the area of GPUs and AI accelerators
• Experience with common programming environments for GPUs and HPC (CUDA, ROCm, OpenCL) 
• Experience with AI frameworks (PyTorch, OpenCV) and operator collections (GGML, Torch-ATen etc.)
• Excellent communication and cross-functional collaboration skills
• Strong product discovery skills including customer interviewing and problem framing
• US Citizenship required

• Pay depends on experience, but we strive to be at the upper end of the salary range
• Health care plan with 100% premium coverage, including medical, dental, and vision.
• 401k with 5% matching.
• Paid Time Off (Uncapped Vacation, plus Sick & Public Holidays).
• Flexible hybrid or remote work arrangement.
• Relocation assistance for qualifying employees.