Principal Engineer - Agentic Optimization & Automation; GPUs

WHAT YOU DO AT AMD CHANGES EVERYTHING

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.

We are building agentic systems that continuously explore, optimize, and maintain performance of AI workloads on AMD Instinct GPUs. Your mission is to design and implement automated performance optimization loops—agents that profile workloads, generate hypotheses, tune kernels and configurations, and push improvements into production with minimal human intervention.

You’ll collaborate with compiler, framework, and infra teams to create the tooling and agentic infrastructure that makes AMD platforms the easiest place to get state-of-the-art performance, at scale.

The ideal candidate is passionate about software engineering and automation, treating performance as a product. You drive sophisticated, multisystem issues to resolution by combining rigorous profiling, data-driven experimentation, and safe automation loops. You communicate effectively and work optimally with compiler, framework, infra/SRE, and customer-facing teams across AMD, aligning stakeholders and landing durable improvements.

• Build and maintain automation that continuously profiles and improves workload performance.
• Implement safe, data-driven tuning of configurations and kernels to achieve measurable gains.
• Detect and triage performance regressions; ensure changes are validated in CI.
• Integrate with existing profiling, compiler, and build/test tooling.
• Produce clear reports and dashboards to communicate results to stakeholders.
• Create reusable tools and interfaces that teams can adopt with minimal effort.
• Partner across teams to prioritize, land, and maintain performance improvements.

• Strong background in GPU performance engineering and systems:

  • Experience profiling and optimizing deep learning workloads on modern accelerators.
  • Familiarity with ROCm, CUDA/HIP, Triton, or similar low-level stacks.

• Experience building automation or optimization systems, such as:

  • Auto-tuning frameworks (e.g., TVM, auto-scheduler, Triton autotune).
  • Experiment management or large-scale benchmarking infrastructure.
  • CI/CD pipelines focused on performance regression tracking.

• Familiarity with LLM/agent tooling:

  • Orchestration frameworks, tool-calling, and structured logging for agents.
  • Applying LLMs to code generation, refactoring, or performance investigation is a plus.
• Strong software engineering skills in Python and at least one of C++/Rust/Go.
• Experience with distributed training/inference and scaling across multi-GPU, multi-node clusters.
• Comfort working cross-functionally with:
  • Framework and compiler teams.
  • Infra/SRE and benchmarking teams.
  • Customer-facing solution engineers.

• B.S./M.S./Ph.D. in Computer Science, Electrical/Computer Engineering, or related field, or equivalent industry experience.

San Jose, CA preferred. May be open to considering other US based locations.

#LI-MV1

#LI-HYBRID

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.