Machine Learning Inference Engineer (Speech Recognition) (offline)

What You'll Do

As a Machine Learning Inference Engineer at the Speech AI Lab at Cisco, you’ll take a central role in building servers that can handle millions of hours of audio streams for running state-of-the-art speech recognition models.

Your goal will be to enable the most efficient execution of deep learning based speech recognition models.


Who You'll Work With

You will work with a team of skilled and creative scientists & engineers to improve our speech technologies by applying machine learning at scale.


Who You Are

- Hands on experience with production quality C++
- Familiarity with GPU Programming (CUDA, OpenCL)
- Hands on experience building software products that handle multimedia streams efficiently
- Familiarity with PyTorch or TensorFlow
- Experience with machine learning model deployment
- Experience working with Machine Learning Scientists to debug and deploy models
- Hands on experience with Kubernetes, Docker, and Helm


Why Cisco?

- You will be a part of an innovative product used by millions of users all around the world
- Annual bonuses
- Medical insurance
- Car allowance
- International multicultural team
- Official employment contract