Principal Software Development Engineer.

At AMD, the mission is to build products that accelerate next-generation computing experiences including AI, data centers, PCs, gaming, and embedded systems. The company emphasizes innovation, collaboration, and solving important challenges with a culture that values execution excellence, humility, and inclusivity.

• Understanding of machine learning techniques and their application in graphics ML model development and optimization such as quantization. - Strong ML development pipeline experience in production environments. - Strong Python/PyTorch development experience from concept to production. - Experience with software development tools such as debuggers, source code control systems (GitHub), and profilers is a plus. - Strong object-oriented programming background; C/C++ preferred. - Effective communication and problem-solving skills. - Good interpersonal skills.

Nice to have: - Proven experience developing and optimizing GPU kernels for ML workloads (e.g., HIP, OpenCL, CUDA, HLSL). - Ability to program in low-level languages (x86 asm, SSE, ISA, Ptx, AMD assembly). - Strong understanding of GPU architecture, graphics APIs (DirectX, OpenGL, Vulkan), and shader programming. - Solid understanding of common neural network operators, their mathematical foundations, and computational requirements. - Master's degree or PhD in Computer Science, Computer Engineering, or equivalent.

Who we're looking for: - Be an influential software engineer passionate about improving performance of key applications and benchmarks. - Work as a member of a core team with the latest hardware and software technology. - Be a hands-on senior engineer passionate about machine learning techniques and software engineering. - Drive sophisticated issues to resolution and communicate effectively across teams.

What you'll be part of: - Research, prototype, and benchmark different ML algorithms from concept to GPU deployment. - Research and prototype quantization techniques for graphics ML algorithms. - Optimize existing ML algorithms using techniques such as quantization. - Collaborate with research, hardware, driver, and compiler teams to analyze and troubleshoot performance issues and improve rendering speed and ML workload efficiency. - Stay current with advancements in GPU hardware, rendering techniques, graphics APIs, and GPU accelerated ML. - Document and share best practices for GPU programming (graphics and compute/ML). - Participate in code reviews and provide constructive feedback.

AMD and its subsidiaries are equal opportunity, inclusive employers considering all applicants without regard to legally protected characteristics. AMD may use Artificial Intelligence to help screen, assess, or select applicants for this position. This posting is for an existing vacancy. AMD does not accept unsolicited resumes from headhunters, recruitment agencies, or fee-based recruitment services.