Software Development Engineer

• Deep Learning & LLM Framework Optimization for AMD GPUs
• Model-Aware Implementation with LLMs and multimodal architectures
• Performance-Conscious Coding in multi-GPU environments
• Profiling using tools to evaluate impact of changes
• End-to-End Performance Engineering across multi-GPU and multi-node setups
• Compiler & Pipeline Acceleration using compiler technologies and graph compilers
• Research & Advanced Techniques like speculative decoding and weight-only quantization
• Cross-Team & Open-Source Collaboration with internal GPU library teams and open-source maintainers
• Software Engineering Excellence for maintainable and production-quality performance optimizations

• Familiarity in Python
• Familiarity with C++ or async programming
• Understanding of LLM or multimodal model concepts
• Knowledge of transformer architectures, attention mechanisms, vision-language alignment, and inference pipelines
• Theoretical grounding in Transformer/Attention/MoE/KV Cache, and quantization (FP8/FP4)
• Linux development environment
• Experience with profiling and diagnosing compute, memory, and communication bottlenecks across multi-GPU and multi-node environments
• Solid Python/C++ coding skills and experience debugging and testing practices
• Experience with multimodal models (e.g., Qwen-VL, Qwen-Image-Edit, Wan) or diffusion-based generative models
• Familiarity with techniques like quantization, PagedAttention, continuous batching, or speculative decoding
• Exposure to GPU computing (ROCm, CUDA) or performance profiling tools (e.g., PyTorch Profiler)
• Experience with distributed inference for large-scale models (e.g., Tensor Parallel, Pipeline Parallel)
• Bachelor's in Computer Science, Computer Engineering, Electrical Engineering, or a related field

• Familiarity with C++ or async programming
• GPU Kernel Development & Optimization using HIP, CUDA, ASM, and tools like CK, CUTLASS, and Triton
• Compiler & System-Level Optimization knowledge of LLVM, ROCm, and compiler-driven techniques
• software engineering excellence & community contribution

AMD benefits at a glance