- Build, manage, and scale production infrastructure across GCP and GPU cloud providers using Kubernetes, Docker, and Terraform.
- Improve inference performance, latency, throughput, GPU utilisation, and infrastructure costs through profiling and experimentation.
- Identify bottlenecks in building, deploying, and serving models, and implement improvements.
- Monitor critical systems and respond to production incidents.
- Make autonomous infrastructure architecture decisions balancing scalability, reliability, performance, and cost.
- Improve deployment pipelines, infrastructure automation, monitoring, and observability.
- Support secure infrastructure practices and enterprise deployment requirements.
DockerPythonGCP+3 more