Ihre Aufgaben:
* Develop and continuously enhance the OneCompiler toolchain, including the MLIR/IREE front end, intermediate representation (IR) transformations, and backend code generation
* Integrate compiler components into software products such as eIQ and ML SDKs
* Design optimization passes and hardware-specific lowering flows for efficient model execution
* Contribute to exploratory compiler initiatives such as training-graph ingestion, auto-tuning, heterogeneous scheduling, and runtime bindings
* Build and maintain model ingestion pipelines for PyTorch, ONNX, TensorFlow, and TFLite
* Collaborate closely with internal engineering teams and external partners to drive innovation across the compiler ecosystem
Ihre Qualifikationen:
* Strong background in compiler design and modern ML compiler frameworks (e.g., MLIR/LLVM, TVM, IREE, XLA)
* Familiarity with model export workflows for PyTorch, ONNX, and TensorFlow
* Deep understanding of AI/ML models, quantization techniques, and hardware-aware optimizations
* Proficiency in C++ and Python, with experience implementing compiler passes or device backends
* Experience working with embedded or heterogeneous compute architectures (e.g., Cortex CPUs, NPUs, DSPs)
* Hands-on experience with IREE AOT compilation or its runtime is benefitical
* Experience developing new MLIR dialects is benefitical
Ihre Vorteile:
* Fascinating, innovative environment in an international atmosphere