AI/ML Compiler & Runtime Software Engineer
GlobalFoundries2 days ago
Pune, IndiaStaff+
Responsibilities
- Architect, design, and develop AI/ML compiler and runtime software for RISC-V IP, NPU, and SoC platforms.
- Develop IREE-based compiler flows covering MLIR lowering, code generation, runtime integration, and edge deployment.
- Create custom MLIR dialects, compiler passes, lowering pipelines, pattern rewrites, and accelerator backends.
- Support AI framework import and lowering paths for PyTorch, ONNX, TensorFlow Lite/TFLite, torch-mlir, TOSA, and Linalg.
- Optimize neural-network workloads through operator fusion, tiling, memory planning, quantization, layout transformation, vectorization, and accelerator-aware scheduling.
- Enable AI execution across CPU, vector, matrix, NPU, DSP, and custom accelerator paths while balancing latency, throughput, memory footprint, and power.
- Bring up and validate workloads on simulators, FPGA platforms, emulation environments, development boards, and silicon.
- Analyze compiler and runtime performance, identify bottlenecks, and optimize graph-, operator-, and kernel-level execution.
- Define technical direction for AI SDK compiler pipelines, runtime interfaces, model deployment flows, and accelerator integration.
- Build test infrastructure, validation flows, benchmark suites, and CI pipelines for correctness, performance, and regression tracking.
- Provide technical leadership and mentorship to engineers developing compiler, runtime, model deployment, and edge AI software.
- Support internal and customer-facing software enablement, debugging, performance tuning, and deployment on target platforms.
Requirements
- 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, pattern rewrites, code generation flows, or custom-hardware backend integration.
- Understanding of IREE code generation, dispatch formation, executable generation, HAL/runtime concepts, and target-specific lowering.
- Experience with AI compiler/runtime stacks for edge AI or accelerator-backed inference.
- Experience with PyTorch, ONNX, TensorFlow Lite/TFLite, and related model conversion or import flows.
- Working knowledge of torch-mlir, TOSA, Linalg, tensor dialects, bufferization, quantization dialects, and MLIR-based model lowering.
- Strong understanding of neural-network execution and optimization, including quantization, operator fusion, tensor layouts, memory planning, tiling, vectorization, and kernel selection.
- Experience optimizing workloads for AI accelerators, NPUs, DSPs, vector processors, matrix engines, or custom SoC IP.
- Strong C/C++ programming skills and Python scripting ability for compiler tooling, testing, automation, and model workflow integration.
- Experience with Linux development environments, cross-compilation, debugging, profiling, build systems, and runtime bring-up.
- Ability to debug across compiler IR, generated code, runtime behavior, and hardware/software interaction.
- Proven ability to technically lead complex software modules, mentor engineers, and drive execution across cross-functional teams.
- Preferred experience with RISC-V, ARM, x86, DSP, GPU, or custom accelerator software stacks.
- Preferred familiarity with RISC-V Vector, matrix acceleration, custom instructions, accelerator-specific code generation, FPGA prototyping, Linux bring-up, board debugging, or pre-silicon validation.
- Preferred exposure to llama.cpp, GGML/GGUF, ONNX Runtime, TensorFlow Lite, TVM, XNNPACK, or similar edge inference frameworks.
- Preferred experience benchmarking and optimizing AI models for vision, audio, transformers, GenAI, robotics, automotive, industrial, or real-time embedded workloads.
- Preferred understanding of hardware/software co-design, memory hierarchy, DMA, scratchpad memory, cache behavior, accelerator data movement, runtime systems, kernel libraries, microkernels, and accelerator runtime APIs.
- Preferred familiarity with Jenkins, Git, CMake, Bazel, Jira, or similar engineering infrastructure.
- Excellent communication and interpersonal skills for explaining compiler and AI runtime concepts to software, hardware, and product stakeholders.
Benefits
- The role is based in Pune or Bangalore, India.
- GlobalFoundries offers an inclusive and equal-opportunity workplace.
- Employment is subject to applicable background checks and medical screenings under local law.
- Benefits information is provided through the GlobalFoundries careers website.
About GlobalFoundries
GlobalFoundries manufactures semiconductors as a contract foundry, offering process technologies, design enablement, and wafer fabrication for chip designers and device makers across automotive, data center, mobile, and IoT markets. Headquartered in Malta, New York and founded in 2009, it operates fabs in the U.S., Europe, and Asia and is listed on Nasdaq (GFS). Customers use its analog/RF, high-voltage, and specialty nodes alongside advanced CMOS.