Founding Deep Learning Deployment Engineer - TL.

About the role

We are seeking a Founding Deep Learning Deployment Engineer to join our startup team. This role will focus on architecting and deploying cutting-edge deep learning solutions using advanced technologies for optimal performance.

Key responsibilities

• Design and implement deployment architectures for deep learning models.

• Optimize models using TensorRT and ONNX for high-performance inference.

• Collaborate with cross-functional teams to integrate deep learning solutions into products.

• Develop and maintain Python packages for model deployment.

• Conduct performance tuning and troubleshooting of deployed models.

• Stay updated with emerging deep learning technologies and methodologies.

• Mentor junior engineers and contribute to team knowledge sharing.

Required qualifications

• 5-7 years of experience in deep learning deployment and architecture.

• Proficient in Python programming and related libraries.

• Hands-on experience with TensorRT and ONNX.

• Strong understanding of deployment practices in a startup environment.

• Ability to work independently and remotely in a fast-paced setting.

Nice to have

• Experience with cloud deployment platforms (e.g., AWS, GCP, Azure).

• Familiarity with containerization technologies like Docker.

• Knowledge of CI/CD pipelines for deep learning applications.