MLOps and AI Infra - Internship

As an MLOps & AI Infrastructure Intern, you will work on building and
optimizing scalable systems that power LLM deployment, proxying, and AI
workloads. This internship offers hands-on exposure to real-world AI
infrastructure - from GPU orchestration and observability to security,
automation, and efficient model serving.

Selected intern's day-to-day responsibilites include:

1. Build and Manage LLM Proxy Systems to route and balance requests across
multiple model providers (OpenAI, Anthropic, local models).
2. Develop Deployment Pipelines using Docker, Kubernetes, or serverless GPU
setups for efficient model serving.
3. Implement Monitoring & Logging with Prometheus, Grafana, or Weights &
Biases to track model performance and system health.
4. Automate Workflows for training, testing, and deployment through CI/CD
pipelines (GitHub Actions, Argo, Jenkins).
5. Enforce Security and RBAC Policies for user access, data encryption, and
secret management.
6. Optimize GPU and API Utilization with metering, caching, and real-time
billing logic.
7. Collaborate on System Architecture to ensure scalability, fault tolerance,
and security-first design.
8. Document Infrastructure and Tools for internal reference and
reproducibility.