Sr. Principal Machine Learning Software Engineer – Inference Serving Engine

Ampere is a semiconductor design company for a new era, leading the future of computing with an innovative approach to CPU design focused on high-performance, energy efficient AI compute.

As a pioneer in the new frontier of energy efficient high-performance computing, Ampere is part of the Softbank Group of companies driving sustainable computing for AI, Cloud, and edge applications.

As a Sr. Principal Machine Learning Software Engineer, you will lead the architecture and development of high-performance AI inference-serving software for Ampere accelerators. You will work across model serving, frameworks, compilers, runtimes, and optimized kernels to enable efficient deployment of modern AI workloads, including generative AI and large language models.

This is a hands‑on technical leadership role for someone who can solve complex systems and performance challenges while influencing the broader AI software and hardware roadmap.

• Architect and build an inference-serving engine that supports and optimizes state-of-the-art AI models on Ampere deep learning accelerators.
• Drive end‑to‑end serving performance, including throughput, latency, tail latency, memory efficiency, scalability, and cost per inference.
• Develop key serving capabilities such as batching and scheduling, KV-cache management, model loading, memory planning, quantization, and multi‑device or distributed inference.
• Collaborate across model‑serving, framework, compiler, runtime, kernel, and hardware teams to deliver a cohesive, high-performance AI software stack.
• Optimize model execution through graph compilation, operator fusion, precision optimization, efficient attention, and hardware‑specific execution strategies.
• Influence future accelerator architecture through hardware/software co‑design, translating real‑world AI workload requirements into product recommendations.
• Establish technical direction, design standards, benchmarking practices, and performance‑validation processes for the serving platform.
• Evaluate, integrate, and contribute to relevant open‑source AI serving and runtime technologies.
• Mentor engineers and lead technical decisions across cross‑functional initiatives.
• Partner with product, field, and customer teams to prioritize capabilities and deliver production‑ready AI solutions.

• Bachelor’s degree in Computer Science, Computer Engineering, Mathematics, Electrical Engineering, or a related technical field with 12+ years of relevant experience; master’s degree with 8+ years; or Ph.D. with 5+ years.
• Experience developing or optimizing production inference runtimes, serving engines, deployment toolkits, or high‑performance AI systems.
• Experience with technologies such as vLLM, llama.cpp, TensorRT/TensorRT-LLM, ONNX Runtime, OpenVINO, Triton Inference Server, TVM, XLA, MLIR, or comparable systems.
• Expert proficiency in modern C++ and strong experience in C, including concurrent programming, memory management, and systems‑level performance optimization.
• Strong understanding of AI inference performance, including batching, scheduling, latency/throughput tradeoffs, memory bandwidth, KV-cache behavior, quantization, and accelerator utilization.
• Experience with profiling, benchmarking, performance analysis, and low‑level systems debugging.
• Demonstrated ability to lead complex cross‑functional technical initiatives and communicate effectively with software, hardware, and product stakeholders.

• Experience with LLM, transformer, multimodal, or generative‑AI inference.
• Experience with AI frameworks and heterogeneous computing technologies such as PyTorch, oneDNN, SYCL, OpenCL, OpenMP, MPI, CUDA, ROCm,…