Runtime Engineer
Our client are on a mission to make AI accessible and impactful without compromising the environment. By building a high-performance, portable compiler, they empower developers to train models in the cloud, deploy them at the edge, and everything in between—all optimized for efficiency and scalability.
This position focuses on advancing sustainable AI development through a high-performance, portable compiler enabling seamless cross-platform deployment and optimized efficiency.
Key Responsibilities
- Develop and improve a multi-target runtime and optimization techniques.
- Prototype, benchmark, and analyze compiler outputs on diverse hardware.
- Collaborate with product teams to enhance architecture for ML engineers.
- Create tools to identify and resolve performance bottlenecks.
Essential Skills
- Strong experience with modern C++ (C++14+).
- Deep knowledge of asynchronous programming and hardware architecture.
- Experience in OS kernel or hypervisor development.
- GPU programming (CUDA/ROCm) and HPC expertise.
- Familiarity with deep learning frameworks (e.g., PyTorch, JAX).
- Advanced degree or equivalent experience in related fields.
