Dawit Assefa

Results-driven Site Reliability Engineer & AI Infrastructure Engineer with over a decade of experience designing, automating, and scaling cloud-native systems. Proven expertise in AWS, Kubernetes (EKS), Terraform, and CI/CD pipelines, with a strong track record of improving reliability, reducing downtime, and ensuring secure, fault-tolerant environments. Recently expanded into Machine Learning Infrastructure and MLOps, leading projects that optimized model serving at scale using Amazon SageMaker Multi-Model Endpoints (MME), Triton Inference Server on EKS, GPU workload orchestration, and EBS-backed model caching. Adept at bridging DevOps and AI Engineering by building infrastructure that accelerates ML workloads while maintaining enterprise-grade security, observability, and resilience. Passionate about automation, observability, and advancing AI reliability engineering. Recognized for architecting production-ready ML platforms, mentoring cross-functional teams, and delivering measurable improvements in system performance, scalability, and operational efficiency.