10+ Senior Ai Architects
Oci Threads · Saudi Arabia · Posted 17 Oct 2026
About the job
OCI-Threads is seeking Senior AI Architects for GPU and LLM infrastructure roles in UAE, KSA, GCC, or remote locations.
Responsibilities
- Deploy enterprise LLMs on high-performance GPU infrastructure
- Optimize and scale LLM inference
- Serve and optimize LLM models
- Design distributed inference and multi-GPU architecture
- Optimize GPU performance and quantization
- Monitor production performance and SLAs
Requirements
- 10+ years of experience
- Expertise in production LLM inference
- Knowledge of NVIDIA GPU clusters
- Experience with bare-metal Kubernetes
- Strong understanding of distributed AI systems
Benefits
- Immediate or short notice joining
Tap Apply on this page to see how to contact the employer. Applying is free: never pay for a job or a visa.