AI/ML Compiler & Runtime Software Engineer

Overview

Sr Staff Engineer for AI/ML compiler and runtime software in the AI SDK team, focused on enabling Physical AI workloads on next-generation RISC-V platforms.

What you'll do

• Architect, design, and develop AI/ML compiler and runtime software for RISC-V IP, NPU, and SoC platforms.
• Build and enhance IREE-based compiler flows, including MLIR lowering, code generation, runtime integration, and deployment paths.
• Create and maintain custom MLIR dialects, compiler passes, and lowering pipelines for mapping AI workloads to accelerator hardware.
• Enable model import paths and lowering across frameworks like PyTorch, ONNX, and TFLite, using MLIR-based conversion flows.
• Optimize neural network execution for edge deployment, including operator fusion, tiling, memory planning, quantization, and scheduling.
• Collaborate with cross-functional teams to bring up AI workloads on simulators, FPGA/emulation environments, and silicon.

What you'll need

• 3-12 years of hands-on software engineering experience in compiler, runtime, embedded software, or AI/ML systems.
• Strong hands-on experience with IREE, LLVM, and MLIR compiler infrastructure.
• Experience developing MLIR dialects, compiler passes, lowering pipelines, and backend integration for custom hardware.
• Good understanding of IREE code generation, dispatch formation, executable generation, and HAL/runtime concepts.
• Experience with AI model formats/frameworks including PyTorch, ONNX, and TensorFlow Lite/TFLite.
• Strong C/C++ programming skills and good Python scripting for compiler tooling and automation.

Details

• Location: Pune / Bangalore – India.