Senior GPU Systems / AI Infrastructure Engineer

We are seeking a senior-level engineer to build and optimize next-generation AI infrastructure powering large-scale model training and inference. This role sits at the intersection of GPU systems, kernel optimization, distributed compute, and high-performance AI workloads. You will work directly on the performance layer of modern AI stacks where milliseconds matter, GPUs are saturated, and inefficiencies translate directly into cost and latency at scale. This is a deeply technical role for engineers who are comfortable working close to the metal and care about squeezing every ounce of performance out of modern accelerators including NVIDIA, AMD, and emerging architectures. Key responsibilities include designing and optimizing GPU kernels using CUDA, Triton, and HIP for large-scale AI workloads, building and tuning high-performance inference and training pipelines for LLMs and multimodal models, and working on distributed systems for AI training across multi-node, multi-GPU clusters. You will improve memory bandwidth utilization, kernel fusion, and compute efficiency while contributing to or extending frameworks like PyTorch, JAX, or custom runtimes. The role involves building tooling for profiling, benchmarking, and performance regression detection, and collaborating closely with ML researchers and infrastructure engineers to remove system bottlenecks. We are looking for candidates with 5-10+ years in systems engineering, HPC, GPU computing, or AI infrastructure, deep experience with CUDA programming and GPU kernel optimization, and strong understanding of parallel computing, memory hierarchies, and compute bottlenecks. Experience with distributed systems, high-performance programming languages, and working on training or inference stacks for large-scale ML models is essential. This position offers the opportunity to work on critical performance layers of AI systems with direct impact on cost, latency, and scalability of frontier AI models.