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

Job Title

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

Role Summary

Work on compiler and runtime software enabling AI workloads on RISC-V IP, NPUs and SoC platforms as part of the AI SDK / Platform Software team. Deliver IREE- and MLIR-based compiler flows, runtime integration, code generation, quantization, and accelerator enablement for edge devices.

Collaborate with architecture, hardware, firmware, FPGA, validation, and product teams to optimize model execution across CPU, vector/matrix units and accelerators.

Experience Level

Senior level. Target experience approximately 3–12 years in compiler, runtime, embedded software, or AI/ML systems.

Responsibilities

Primary responsibilities include design, implementation and validation of compiler and runtime components for accelerator-backed inference on edge platforms.

• Architect and implement IREE/MLIR-based compiler flows, MLIR dialects, passes, lowering pipelines, and backend code generation.
• Integrate framework import paths (PyTorch, ONNX, TFLite) and enable lowering via torch-mlir, TOSA, Linalg, etc.
• Optimize models for edge deployment: operator fusion, tiling, memory planning, quantization, layout transforms, and scheduling.
• Enable execution across CPU, vector/matrix units, NPUs and accelerators with attention to latency, throughput and power.
• Collaborate with architecture, hardware, firmware and validation teams for bring-up on simulators, FPGA, emulation and silicon.
• Analyze performance, identify compiler/runtime bottlenecks and implement optimizations at graph, operator and kernel levels.
• Define software architecture and technical direction for AI SDK components and deployment flows.
• Build test infrastructure, benchmarks and CI for correctness, performance and regression tracking.
• Provide technical leadership and mentor engineers on compiler/runtime enablement and platform software.

Requirements

Required technical skills and experience for the role.

Must-have:

• 3–12 years of software engineering experience in compiler, runtime, embedded or AI/ML systems.
• Hands-on experience with IREE, LLVM and MLIR; developing MLIR dialects, passes, lowering and backend integration.
• Strong C/C++ skills and Python for tooling, tests and automation.
• Experience with AI frameworks and model formats (PyTorch, ONNX, TensorFlow Lite) and conversion/import flows.
• Knowledge of quantization, operator fusion, memory planning, tiling, vectorization and kernel selection.
• Linux development experience: cross-compilation, debugging, profiling and runtime bring-up.
• Experience enabling or optimizing workloads for NPUs, DSPs, vector/matrix units or custom accelerators.
• Proven ability to lead technical efforts and work with cross-functional hardware and firmware teams.

Nice-to-have:

• Experience with RISC-V, RISC-V Vector extensions, ARM, x86, GPUs or custom accelerators.
• Familiarity with FPGA prototyping, board bring-up, simulators, or early silicon validation.
• Exposure to LLM and edge inference stacks and benchmarking (e.g., llama.cpp, ONNX Runtime, TVM, XNNPACK).
• Familiarity with CI/CD and build tools such as Jenkins, CMake, Bazel and Git.

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.