Job Summary
Implement and validate new model architectures in a simulator to assess hardware requirements ahead of silicon production. In this role, you will work with cross-functional teams to streamline model bring-up and support high-performance inference.
Responsibilities
- Implement new model architectures in a simulation environment.
- Verify model behavior and evaluate hardware requirements before silicon is produced.
- Partner with teams across functions to automate and improve the model bring-up process.
- Help ensure inference performance meets demanding requirements.
Qualifications
- At least 4 years of experience in ML systems or inference engineering.
- Strong programming skills in Rust or C++, along with Python proficiency.
- In-depth knowledge of transformer internals, quantization, and model inference frameworks.


