Location: Germany
About Us
Be part of a team building ultra energy-efficient infrastructure for next-generation AI inference. Leveraging dynamic sparsity and brain-inspired computing architectures, we’re pioneering radically more efficient paths for GenAI algorithms.
What You’ll Do
- Design, implement, and optimize MLIR-based compiler frameworks for our brain-inspired AI hardware.
- Collaborate closely with hardware and software teams to map dynamic sparsity algorithms efficiently to our architecture.
- Develop new compiler passes, transformations, and optimizations tailored for energy-efficient AI workloads.
- Profile and analyze compiler performance to identify and eliminate bottlenecks.
- Contribute to open-source compiler technologies where applicable.
What We’re Looking For
- 4+ years of experience as a compiler engineer or developer, ideally with a focus on MLIR, LLVM, or related frameworks.
- Strong knowledge of compiler design, intermediate representations, and optimization techniques.
- Experience with AI/ML frameworks (e.g., TensorFlow, PyTorch) and their compiler stacks is a plus.
- Familiarity with hardware-aware optimization (e.g., for GPUs, accelerators, or custom architectures).
