What are the responsibilities and job description for the Machine Learning Runtime Optimization Engineer position at Interop Labs?
Machine Learning Runtime Optimization Engineer
We are seeking a skilled Machine Learning Runtime Optimization Engineer to join our innovative project, redefining software.
Responsibilities:
- Optimize ML inference engines (ONNX Runtime, TensorRT, CoreML, etc.) and models for deployment.
- Work with Mac/Linux-based runtimes and heterogeneous compute environments (CPU/GPU/NPUs).
- Apply numerical optimization, compiler techniques, and low-level performance tuning.
About the Role:
This role involves focusing on backend optimizations for ML runtimes, including hardware acceleration and inference speed improvements. Our ideal candidate will have experience with ML inference engines and model optimization, proficiency in Mac/Linux-based runtimes, and a deep understanding of numerical optimization and compiler techniques.
We welcome open-minded individuals with a PhD in optimization, systems, machine learning, or related fields. You will be part of an autonomous, distributed environment, working collaboratively in a diverse team worldwide.
You will have scope to contribute to high-impact work and make a difference in a decentralized protocol. Additionally, you will have the opportunity to challenge yourself while learning, enjoying unlimited time off throughout the year to rest and recharge.
Our compensation package includes competitive salary and stock options, with potential for growth from the initial phase.