AI/ML Compiler & Runtime Software Engineer
GlobalFoundries16 hours ago
Pune, IndiaStaff+
Responsibilities
- Architect, design, and develop AI/ML compiler and runtime software for RISC-V IP, NPUs, and SoC platforms.
- Develop IREE compiler flows covering MLIR lowering, code generation, runtime integration, and edge AI deployment.
- Create custom MLIR dialects, compiler passes, lowering pipelines, pattern rewrites, and hardware-specific code-generation flows.
- 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, and NPU acceleration paths while balancing latency, throughput, memory footprint, and power efficiency.
- Collaborate with architecture, hardware, firmware, FPGA, validation, product, and customer-facing teams on workload bring-up and enablement.
- Analyze compiler and runtime performance, identify bottlenecks, and drive graph-, operator-, and kernel-level optimizations.
- Define technical direction for compiler pipelines, runtime interfaces, model deployment flows, and accelerator integration.
- Build correctness, validation, benchmarking, regression-tracking, and CI infrastructure for AI compiler and runtime software.
- Provide technical leadership, mentorship, debugging support, performance tuning, and deployment assistance for AI software workloads.
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 integrations.
- Understanding of IREE code generation, dispatch formation, executable generation, HAL/runtime concepts, and target-specific lowering.
- Experience with AI model formats and frameworks such as PyTorch, ONNX, TensorFlow Lite/TFLite, and related 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 work with architecture and hardware teams to translate accelerator capabilities into compiler and runtime enablement.
- 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, FPGA prototyping, Linux bring-up, board debugging, and pre-silicon validation.
- Preferred exposure to llama.cpp, GGML/GGUF, ONNX Runtime, TensorFlow Lite, TVM, XNNPACK, AI model benchmarking, and edge inference optimization.
- 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, customer-facing enablement, silicon bring-up, platform software, and SDK delivery.
Benefits
- The position is located in Pune or Bangalore, India.
- GlobalFoundries offers an inclusive and diverse workplace and is an equal opportunity employer.
- Employment offers are conditioned on successful background checks and applicable medical screenings, subject to 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.