Software Engineer, Inference Infrastructure
- Develop an end-to-end video processing pipeline that processes multimodal data (images, audio, etc.) in a video to fit the required format for models.
- Deploy ML models, ensuring consistent and optimal performance in both cloud (like AWS, Azure, GCP) and on-premise environments.
- Collaborate closely with DevOps and system engineering teams to ensure seamless deployments, rollbacks, and updates.
- Engage in troubleshooting and quick resolution of any deployment-related issues, ensuring minimal downtime and optimal user experience.
You may be a good fit if you have:
- Proficiency in Python and Go
- 3 years + experience in building and designing ML infrastructure.
- 5 years + software development experience, including experience in building ML infrastructure.
- Strong understanding of container ecosystems such as Docker and Kubernetes.
- Experience in deploying AI/ML models on cloud platforms such as AWS, Azure, GCP.
- Ability to communicate effectively in English with individuals from diverse language backgrounds and different timezones
- MS or PhD in Computer Science, Math, or equivalent real-world experience
- Experience in leading a team of engineers
- Experience in training deep learning models
- Experience in model deployment using Triton and TensorRT
- Proficiency in GPU Computing (i.e. CUDA)