Location
menlyn
Job Type
Full-time
Posted
June 09, 2026
Job Description
SUMMARY:
ESSENTIAL SKILLS:
- Cloud infrastructure engineering (Azure preferred) with a focus on high-availability, scalable AI platforms (Kubernetes, container orchestration, networking, IAM).
- Strong hands-on experience with Kubernetes (AKS), Helm, and platform-level CI/CD pipelines.
- Solid understanding of conversational AI architectures (LLM-based services, APIs, grounding layers, vector stores).
- Infrastructure-as-Code expertise (Terraform, ARM/Bicep) for reproducible and compliant environments. Security-by-design mindset: identity, secrets management, network isolation, and secure service communication.
- Observability fundamentals: logging, metrics, tracing for AI workloads (latency, token usage, cost drivers). Strong collaboration skills with Dev, Data Science, and Product to translate functional requirements into resilient infrastructure.
- Expe...