onsite
Software Engineer Intern - AI Infrastructure
Software Engineer
Internship for a software engineer building scalable AI infrastructure, focusing on GPU orchestration, model serving, performance optimization, and reliable production pipelines using Python, CUDA, and cloud services.
About the role
Key Responsibilities
- Design and implement scalable model serving and inference pipelines for multimodal AI models.
- Develop and maintain distributed GPU orchestration systems using Kubernetes and container technologies.
- Optimize performance and cost of training and inference workloads through profiling, caching, and hardware‑specific tuning.
- Build observability, monitoring, and alerting solutions to ensure high reliability and rapid issue resolution.
- Collaborate with applied scientists and product teams to create developer‑friendly platforms that accelerate model experimentation.
Requirements
- Currently pursuing a degree in Computer Science, Electrical Engineering, or a related field.
- Proficiency in Python and experience with GPU programming (CUDA or similar).
- Familiarity with container orchestration (Kubernetes, Docker) and cloud platforms such as AWS.
- Understanding of deep learning frameworks like TensorFlow or PyTorch.
- Strong problem‑solving skills, ability to work in a fast‑paced team, and passion for AI infrastructure.
Skills
pythoncudakubernetestensorflowpytorchawslinux