Principal AI Performance and Tools

Advanced Micro Devices, Inc.; Oregon; On-site; USD 150,000 - 210,000; Full time

Job summary

Advanced Micro Devices, Inc. seeks a senior AI performance leader to shape product direction, performance benchmarking strategy, and developer tools across AMD AI software.

You will partner with engineering, architecture, developer relations, and strategic customers to ensure AMD AI platforms deliver top-tier performance, usability, and value across inference, training, and emerging AI workloads. You will translate complex customer needs into actionable product requirements, roadmaps, and

Qualifications

• Proven years of experience in software engineering, systems architecture, performance engineering, AI/ML infrastructure, or related disciplines.
• Hands-on expertise with AI and ML frameworks and runtimes such as PyTorch, TensorFlow, ONNX Runtime, vLLM, or similar technologies.
• Strong understanding of GPU computing, heterogeneous systems, model serving, and AI optimization.
• Experience with performance profiling, benchmarking, tracing, debugging, compiler technologies, runtimes, or systems observability.
• Proficiency in one or more programming languages, including Python, C++, CUDA, or HIP.
• Demonstrated ability to analyze complex system performance behavior and communicate findings clearly to tech and exec audiences.

Responsibilities

• Lead the technical strategy for AI performance analysis, benchmarking, profiling, optimization, and tooling across AMD platforms.
• Partner with customers and internal teams to define product requirements, roadmaps, and measurable success criteria for AI performance and tooling.
• Analyze inference and training workloads across models/frameworks to identify bottlenecks and propose architectural improvements.
• Develop rigorous performance narratives, benchmark methodologies, workload characterization, and competitive analyses.
• Influence roadmaps for profiling, debugging, observability, compilers, runtimes, and performance-tuning tools across AMD's AI software ecosystem.

Skills

Al/ML infra

PyTorch

TensorFlow

CUDA

C++

Performance profiling

Cross-functional collab

Education

BS/MS in CS/CE/EE

Tools

ONNX Runtime

vLLM

ROCm

HIP

Kubernetes

Triton

Job description

ADVANCE YOUR CAREER. ADVANCE THE WORLD.

At AMD, we believe technology has the power to solve the world’s most important challenges. From advancing healthcare and scientific discovery to powering AI and the technologies people rely on every day, innovation at AMD is shaping the future.

Whether you're redesigning next-gen processors, enabling AI breakthroughs, or bringing leading edge products to market, every role at AMD contributes to something bigger— technology that moves the world forward. Join us and, together, we’ll advance your career.

THE ROLE:

Shape the product direction, performance benchmarking strategy, and developer tools ecosystem for AMD Al software. You will be a partner with engineering, architecture, developer relations, and strategic customers to ensure AMD Al platforms deliver outstanding performance, usability, and value across inference, training and emerging Al workloads.

You will serve as a technical authority on Al workload performance, translating complex customer and ecosystem needs into actionable product requirements, performance roadmaps, benchmark methodologies, reference workflows, and go-to-market guidance.

THE PERSON:

The ideal candidate combines deep technical credibility with strong product judgment and customer empathy. You can move fluidly from low-level performance analysis to high-level product strategy, explain complex tradeoffs to technical and executive audiences, and align teams with competing priorities. You are passionate about emerging Al optimizations, algorithms and workloads. You influence effectively without direct authority, communicate clearly, and bring rigor to performance methodology, benchmarking, and developer experience.

KEY RESPONSIBILITIES:

• Lead the technical strategy for Al performance analysis, benchmarking, profiling, optimization, and tools across AMD platforms.
• Partner with external customers and internal stakeholders to define product requirements, roadmap priorities, and measurable success criteria for Al performance and tooling initiatives.
• Analyze inference and training workloads across leading models, frameworks, and deployment environments to identify bottlenecks and recommend architectural and software improvements.
• Develop technically rigorous performance narratives, including benchmark methodologies, workload characterization, competitive analysis.
• Influence roadmaps for profiling, debugging, observability, compilers, runtimes, and performance‑tuning tools across AMD's Al software ecosystem.
• Translate customer requirements and performance gaps into prioritized engineering features, fixes, and optimization initiatives.
• Engage strategic customers, cloud service providers, OEMs, ISVs, Al companies, and open‑source communities to understand real world development workflows and tooling needs.
• Define reference workflows, best practices, and reproducible methodologies for optimizing Al models and applications.
• Collaborate with developer relations, solutions architecture, marketing, and sales teams to communicate AMD's technical capabilities and accelerate adoption.
• Represent AMD in customer briefings, technical forums, industry events, standards organizations, and open‑source communities, as appropriate.

PREFERRED EXPERIENCE:

• Proven years of experience in software engineering, systems architecture, performance engineering, Al/ML infrastructure, developer tools, or related disciplines.
• Hands‑on expertise with Al and machine learning frameworks and runtimes such as PyTorch, TensorFlow, JAX, ONNX Runtime, vLLM, or similar technologies.
• Strong understanding of GPU computing, heterogeneous systems, model serving, and Al optimization.
• Experience with performance profiling, benchmarking, tracing, debugging, compiler technologies, runtimes, or systems observability.
• Proficiency in one or more programming languages, including Python, C++, C, HIP, CUDA, or similar languages.
• Demonstrated ability to analyze complex system performance behavior and communicate findings clearly to technical and executive audiences.
• Experience influencing cross functional product and engineering roadmaps without direct reporting authority.
• Strong product judgment, customer empathy, and the ability to balance technical depth with business and ecosystem priorities.
• Excellent written, verbal, and presentation skills.
• Experience with AMD ROCm ™ , HIP,Triton, FlyDSL, vLLM, SGLang, distributed computing libraries, or open source Al frameworks and libraries.
• Experience optimizing large language models, generative Al, recommendation systems, computer vision, or scientific computing workloads.
• Familiarity with cloud Al platforms, Kubernetes‑based deployments, model‑serving stacks, and enterprise Al operations.
• Contributions to open‑source projects, published technical work, patents, or recognized expertise in Al systems or performance engineering.
• Experience working with major cloud providers, server OEMs, Al startups, or enterprise customers.

ACADEMIC CREDENTIALS:

• B.S. or M.S. in Computer Science, Computer Engineering, Electrical Engineering, Business, or a related field.

LOCATION:

• San Jose, CA or Austin, TX preferred.
• Other locations may be considered.

This role is not eligible for visa sponsorship.

Benefits offered are described: AMD benefits at a glance.

AMD does not accept unsolicited resumes from headhunters, recruitment agencies, or fee‑based recruitment services. AMD and its subsidiaries are equal opportunity, inclusive employers and will consider all applicants without regard to age, ancestry, color, marital status, medical condition, mental or physical disability, national origin, race, religion, political and/or third‑party affiliation, sex, pregnancy, sexual orientation, gender identity, military or veteran status, or any other characteristic protected by law. We encourage applications from all qualified candidates and will accommodate applicants’ needs under the respective laws throughout all stages of the recruitment and selection process.

AMD may use Artificial Intelligence to help screen, assess or select applicants for this position. AMD’s “Responsible AI Policy” is available here.

This posting is for an existing vacancy.