AI/ML Compiler & Runtime Software Engineer
GlobalFoundries (company site, opens in a new tab)3–12 yrsPuneOn-siteDirect career pageEst. 35–65 LPA
Posted on 11 Sept
Reach people at GlobalFoundries
People at this company you can reach
Log in to see who works here
Create a free account or log in to see the people at GlobalFoundries you could write to:
- Recruiters & HR
- People in this function
- Work addresses
Your match
Against your primary resume
Log in to see your match score
Create a free account or log in to unlock your CV match score across:
- Role fit
- Experience
- Industry relevance
Protocol Intelligence
How competitive this role is
Competition
Background fit
Strictness
Log in to see why each signal reads the way it does.
Job description
Structured overview of role & requirements
About This Role
- Own architecture, design, and development of AI/ML compiler and runtime software targeting RISC-V IP, NPU, and SoC platforms, focusing on efficient execution of AI models for edge devices.
- Develop and maintain compiler flows based on IREE and MLIR infrastructure including custom dialects, passes, lowering pipelines, code generation, and integration for hardware accelerators.
- Lead cross-functional collaboration with hardware, firmware, validation, and product teams for bringing up AI workloads on simulators, FPGA, emulation, and silicon platforms and deliver runtime optimizations.
Minimum Requirements
- 3-12 years of hands-on software engineering experience, preferably in compiler, runtime, embedded software, or AI/ML systems.
- Strong experience with IREE, LLVM, MLIR compiler infrastructure including developing MLIR dialects and compiler passes.
- Proficient in C/C++ and Python scripting for tooling, testing, and automation targeting Linux development and cross-compilation environments.
- Location: Pune or Bangalore, India (implied; onsite or hybrid mode not explicitly mentioned).
Ideal Candidate Profile
- Experienced in AI compiler/runtime stacks for edge AI and accelerator-backed inference, with deep knowledge of model formats like PyTorch, ONNX, TFLite and MLIR-based model lowering.
- Demonstrated ability to provide technical leadership for complex software modules and to work at the intersection of software and hardware by collaborating with architecture and hardware teams.
- Hands-on experience with AI hardware accelerators (NPU, DSP, vector/matrix engines) and runtime optimization techniques like quantization, operator fusion, tiling, and memory planning for real-time and low-power AI workloads.