AI Performance Engineer (Life Sciences)

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 designing 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 We are looking for an AI Performance Engineer, Life Sciences to contribute to the development and optimization of foundation models and agentic AI systems for drug discovery. You will work within a multidisciplinary team of machine learning researchers, computational chemists, and software engineers to deliver AI systems with real-world therapeutic impact. This role offers the opportunity to apply expertise in deep learning performance optimization, collaborate across technical domains, and deliver production-grade software solutions. Main Responsibilities Optimize machine learning models through profiling, bottleneck analysis, and efficient mapping of workloads to GPU architectures. Analyze emerging machine learning models, understand their compute and memory requirements, and optimize them for training and inference across a range of hardware platforms. Perform optimization at the kernel, framework, and hardware levels. Work hands-on with deep learning and transformer architectures, as well as physics-based simulation models. Profile and analyze workloads on current hardware, identify performance bottlenecks, and develop strategies to improve efficiency and scalability. COLLABORATION Contribute to the Life Sciences workstream within AMD Silo AI’s R&D and Models unit as part of an interdisciplinary team. Partner with life sciences AI developers and domain experts to understand requirements and translate them into effective technical solutions. Share knowledge, experience, and best practices with the wider team through training, mentoring, and collaboration. Collaborate with teams located in Finland and internationally across the organization. Engage with clients to explain performance bottlenecks, optimization opportunities, and proposed solutions clearly and effectively. MAIN GOALS FOR THE FIRST SIX MONTHS Benchmark, analyze, and optimize the performance of key machine learning applications on single and multi-GPU systems at the kernel, framework, and hardware levels. Design, implement, and test GPU kernels and algorithms for tensor operations, including matrix multiplication and convolutions used in high-performance machine learning libraries and frameworks. Identify architectural opportunities to improve the performance of transformer-based and deep learning architectures. Communicate learnings, outcomes, and impact to internal and external stakeholders in a clear, structured, and effective way. Deliver high-quality, maintainable code and documentation aligned with open-source software development best practices. What You’ll Bring SKILLS AND QUALIFICATIONS A Master’s degree, PhD, or equivalent practical experience in Computer Science, Computer Engineering, Computational Science, Applied Mathematics, Cheminformatics, Bioinformatics, or a related field. Relevant experience developing and delivering machine learning, simulation, or high-performance computing solutions. Experience building machine learning and simulation applications and pipelines. A strong understanding of deep learning architectures, including transformers, diffusion models, and language models. Proficiency in Python and familiarity with C++ in production environments. Experience with PyTorch; familiarity with JAX would be beneficial. Software engineering skills across rapid prototyping, debugging, profiling, optimization, and the delivery of maintainable production code. Familiarity with AI-assisted development tools, such as Claude Code or Cursor. Experience with performance profiling tools such as rocprof, PyTorch Profiler, or Nsight. Experience with framework-level optimization, including compilation techniques and backends such as Inductor or TensorRT. Experience profiling and optimizing GPU workloads using ROCm and/or CUDA. GPU software development experience using technologies such as HIP, CUDA, or OpenCL. Experience developing GPU kernels with HIP, CUDA, or Triton. Experience working in high-performance computing environments. Effective written and verbal communication and presentation skills in English. Additional Valued Experience Experience building and operating large-scale machine learning systems, including training infrastructure and distributed computing environments. Understanding of GPU architectures and low-level optimization techniques, including memory hierarchy, instruction scheduling, and performance trade-offs. Experience developing, maintaining, and supporting open-sou