Experience with any cloud-based Kubernetes or container orchestration solution such as SPCS- Snowpark Container Services (preferred), ECS, EKS, GKE, Cloud Run, etc.
Knowledge of deploying and serving LLMs on multi-node GPU clusters (Ray Serve, etc. ) (would be excellent to have).
Key Responsibilities :
Develop robust REST API services using Python frameworks such as FastAPI or Flask.
Build and maintain containerized multi-service applications deployed on cloud environments.
Develop and deploy Snowflake Native Applications (experience or familiarity).
Manage advanced Docker setups, including volume mounts, Compose YAML, container networking, and GPU-enabled containers (nvidia-docker).
Utilize cloud-based Kubernetes or container orchestration platforms such as SPCS (Snowpark Container Services), ECS, EKS, GKE, Cloud Run, or equivalent.
Collaborate with data science teams to deploy and serve large language models (LLMs) on multi-node GPU clusters using tools like Ray Serve (preferred).
Participate in code reviews, troubleshooting, and performance optimization.
Ensure data privacy, security compliance, and maintain best practices for cloud-native deployments.