Software Applications Engineer (GPU Machine Learning End-to-End Performance)

Advanced Micro Devices Voir toutes les offres

  • Markham, ON
  • Permanent
  • Temps-plein
  • Il y a 1 mois
Job Description:WHAT YOU DO AT AMD CHANGES EVERYTHINGAt 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 ROLE:AMD’s Advanced Technology Group is an entrepreneurial research and development team to build AMD's future advanced platforms & products. Our teams work closely with outside customers and internal teams to develop hardware, software, and systems solutions into next generation computing platforms. As part of AMD Advanced Technology Group, you will have the opportunity to be part of a winning team that will collaborate with internal teams & customers, explore new platform technologies, and lead the development of best-in-class hardware, software, and systems technologies that our customers will use for real-world problems.In this role, you will join our team working on AMD’s next generation GPU edge inference solutions, ensuring machine learning solutions hit performance goals through GPU performance analysis, profiling, workload optimization and other duties to unlock powerful experiences for end-users with AMD devices. We are looking for someone who is passionate about using AI agents, building automation frameworks, and GPU-aware analysis tools to optimize machine learning models and inference systems. This role focuses on building tooling that can automatically transform and optimize ML models, visualize model execution and identify bottlenecks, and use AI agents to accelerate development, debugging, and performance tuning.This role sits at the intersection of ML system optimization, GPU compute, and AI-assisted tooling development—ideal for someone excited about building the next generation of model optimization infrastructure.THE PERSON:AMD is looking for a Member of Technical Staff to join our Advanced Technology Group GPU based Machine Learning development to work on AMD’s long-term Graphics and Machine Learning solutions, which will have significant impact for AMD, and the future of our products.Our group works on forward-looking projects and novel system concepts that significantly impact AMD’s future product portfolio. Your role will contribute to shaping AMD’s forward-looking hardware and software technologies.KEY RESPONSIBILITIES:
  • Work within a team on Machine Learning SW and Workload development in pre and post-silicon phases of product development enabling next-generation of ML workloads in functional and performance attainment.
  • Develop tools that analyze ML model graphs and automatically suggest or perform optimizations (layout changes, fusion, quantization, packing strategies).
  • Build AI-assisted visualization tools to identify bottlenecks, inefficient memory patterns, operator hotspots, or scheduler issues.
  • Integrate AI agents to automate tasks such as code generation, performance diagnosis, or graph rewriting.
  • Contribute to internal tools that visualize GPU memory use, async compute overlap, and tensor residency.
  • Build ML kernels, microbenchmarks, operators, optimizing for topics such as tile sizes, block configs, memory layouts to achieve optimized performance.
  • Collaborate across kernel, runtime, and model teams; participate in code reviews and design discussions.
  • Collaborate with inter-disciplinary teams to improve system-level efficiency, end-to-end performance, and power.
PREFERRED EXPERIENCE:
  • Experience with at least one of the following:
  • Model transformation tools (ONNX, TensorRT, OpenVINO etc).
  • Kernel technologies (CUDA, HIP, Vulkan compute).
  • Strong programming skills in Python and/or C++.
  • Experience building tools or pipelines using AI agents, LLMs, or automation frameworks.
  • Understanding of machine learning architectures, for example transformer basics (attention, tensor shapes, KV caching, memory patterns).
  • Ability to interpret profiling output (ROCm tools, PyTorch profiler, Nsight, Perfetto).
  • Comfortable working in exploratory environments and iterating on tool ideas quickly.
  • Track record in using AI tooling to accelerate engineering work.
  • Strong collaboration and communication skills.
ACADEMIC CREDENTIALS:
  • Master / Bachelor of Computer Systems, Computer Science, Software Engineering, or similar degree.
#LI-TB1#LI-HybridBenefits offered are described: .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 availableThis posting is for an existing vacancy.

Advanced Micro Devices