Job description:
Core Requirements:
- Minimum 3+ years experience with cloud infrastructure for ML model deployment, specifically:
+ creating clusters of VMs with load-balancing
+ dockerisation
+ Kubernetes for hosting GPU-dependent Docker images
+ high-throughput, low-latency hosting of Python-based ML models
+ creating customised VPNs, Blobs/S3, and No-SQL DBs
- Very strong experience and track record of taking Python-based ML models and scaling them out for 10k concurrent users
using Kubernetes for hosting and load-balancing
- Strong all around Kubernetes and Docker experience (ML focused) with either Azure, AWS, or Google Cloud variants
- Strong knowledge and understanding of HTTP, Websockets, and AMQP
- Strong knowledge of how to correctly configure horizontal scaling in Kubernetes for GPU-based resources