Sr Staff Engineer — AI/ML Compiler & Runtime Software Engineer

Job Title

Sr Staff Engineer — AI/ML Compiler & Runtime Software Engineer

Role Summary

Join the Platform Software & AI SDK team to design and implement AI/ML compiler and runtime software for RISC-V IP, NPUs, and SoC platforms. The role spans compiler engineering, runtime systems, code generation, quantization, and hardware-software co-design to enable efficient edge AI execution.

Experience Level

Senior-level role. The posting indicates 3–12 years of hands-on software engineering experience, with leadership and cross-functional collaboration expectations.

Responsibilities

Key responsibilities include developing compiler and runtime components, optimizing AI workloads for accelerators, and leading technical delivery.

• Architect, design, and implement AI/ML compiler and runtime software for RISC-V, NPU, and SoC platforms.
• Develop and enhance IREE-based compiler flows, including MLIR lowering, code generation, and runtime integration.
• Create and maintain custom MLIR dialects, compiler passes, lowering pipelines, and transformation flows.
• Support AI framework import paths (PyTorch, ONNX, TFLite) and enable lowering via torch-mlir, TOSA, Linalg, etc.
• Optimize neural networks for edge deployment: operator fusion, tiling, memory planning, quantization, and layout transforms.
• Enable execution across CPU, vector/matrix units, and NPU acceleration paths while balancing latency, throughput, memory, and power.
• Collaborate with architecture, hardware, firmware, FPGA, validation, and product teams for bring-up on simulators, FPGA, emulators, and silicon.
• Analyze model performance, identify compiler/runtime bottlenecks, and implement optimizations at graph, operator, and kernel levels.
• Define software architecture and technical direction for AI SDK components, including deployment flows and accelerator integration.
• Build test infrastructure, benchmarks, and CI pipelines; provide technical leadership and customer enablement for platform software.

Requirements

Must-have technical skills and experience required to succeed in this role, followed by useful additions.

Must-have:

• 3–12 years of software engineering experience with substantial compiler, runtime, embedded software, or AI/ML systems work.
• Hands-on experience with IREE, LLVM, and MLIR: developing dialects, passes, lowering pipelines, pattern rewrites, and backend integration.
• Strong understanding of IREE code generation flow, dispatch formation, executable generation, and HAL/runtime concepts.
• Experience with AI model formats and frameworks (PyTorch, ONNX, TensorFlow Lite) and related import/conversion flows.
• Proficiency in C/C++ and Python for compiler tooling, testing, and automation; experience in Linux development, cross-compilation, debugging, and profiling.
• Deep knowledge of neural network optimization: quantization, operator fusion, tensor layouts, memory planning, tiling, and kernel selection.
• Experience enabling or optimizing workloads for AI accelerators, NPUs, DSPs, or custom SoC IP; ability to collaborate with hardware/architecture teams.
• Proven technical leadership, mentoring ability, and experience driving cross-functional execution.

Nice-to-have:

• Experience with RISC-V, ARM, x86, DSP, GPU, or custom accelerator toolchains and RISC-V vector/matrix acceleration concepts.
• Familiarity with FPGA prototyping, board bring-up, emulation, or early silicon validation.
• Exposure to LLM and edge inference stacks (llama.cpp, GGML, ONNX Runtime, TVM, XNNPACK) and edge benchmarking.
• Familiarity with CI/CD and build tools such as Jenkins, CMake, Bazel, Git, and Jira.

Education Requirements

Not specified.

About the Company

Company: GlobalFoundries

Headquarters: Saratoga Springs, New York, USA

GlobalFoundries is a leading contract manufacturer for the global semiconductor industry, with facilities in multiple countries, including the USA. The company develops a broad portfolio of semiconductor technologies and employs around 13,000 people worldwide. GlobalFoundries focuses on enhancing competitiveness in specialized application solutions and fostering innovation in mobile communications, consumer electronics, and automotive applications.