Senior ROCm Product Manager, Triton & DSL Strategy

Advanced Micro Devices, Inc•Santa Clara, CA

14d•Hybrid

About The Position

At AMD, our mission is to build great products that accelerate next-generation computing experiences—from AI and data centers, to PCs, gaming and embedded systems. Grounded in a culture of innovation and collaboration, we believe real progress comes from bold ideas, human ingenuity and a shared passion to create something extraordinary. When you join AMD, you’ll discover the real differentiator is our culture. We push the limits of innovation to solve the world’s most important challenges—striving for execution excellence, while being direct, humble, collaborative, and inclusive of diverse perspectives. Join us as we shape the future of AI and beyond. Together, we advance your career. THE TEAM: AMD’s Data Center GPU organization builds high-performance GPUs for largescale machine learning. The Triton compiler and kernel teams are central to unlocking performance, stability, and usability of AMD Instinct™ GPUs in the world’s most demanding training environments. This is not a SaaS role. Success is measured by software quality delivered to customer managed, on-premise systems: performance, correctness, stability, compatibility, and developer experience. THE ROLE: AMD is seeking a Product Manager to own the strategy, roadmap, and execution for the Triton compiler and kernel software stack. You will lead opensource and customer facing deliverables that enable high-performance ML workloads on AMD GPUs. You will partner closely with compiler, kernel, runtime, performance, QA, and framework teams. While you will not write production code, the role requires strong technical fluency and the ability to drive priorities across complex system level tradeoffs. Regular, direct customer engagement is a core expectation.

Requirements

Solid background in technical product management for systems software, compilers, ML infrastructure, GPU software, or developer platforms.
Familiarity with compiler concepts (LLVM/MLIR), GPU kernels, or performance critical software.
Experience working with opensource projects.
Exposure to largescale ML training environments and on-prem deployments.
Bachelor’s degree in Computer Science, Engineering, or related field, or equivalent
This role is not eligible for visa sponsorship.

Responsibilities

Own the Triton compiler and kernel roadmap, driving improvements in performance, correctness, portability, and usability.
Translate customer and ecosystem needs into clear requirements, milestones, and measurable outcomes.
Balance priorities across features, performance optimization, bug fixes, stability, upstream contributions, and releases.
Ensure high-quality on-prem software delivery through strong release readiness, testing, CI quality, and regression prevention.
Act as the customer voice through regular engagement with research, infrastructure, and training teams.
Lead opensource engagement, including upstream contributions, issue triage, and community collaboration.
Establish strong operational cadence, execution tracking, and customer focused metrics.