Bachelor’s degree in Computer Science, Computer Engineering, or a related technical discipline, or equivalent experience
5+ years of experience designing, deploying,operating, and troubleshooting modern cloud-based and on-premises infrastructure, DevOps platforms, or SaaS/PaaS environments
Hands-on experience building and supporting production AI applications, including LLM applications, AI agents, workflow automation, or generative AI solutions
Strong understanding of the LLM application stack, including prompt engineering, retrieval-augmented generation (RAG), embeddings, vector search, reranking, context management, structured outputs, tool use, evaluation, and AI security practices
Experience with AWS generative AI technologies, including Amazon Bedrock andAgentCore, as well as agentic orchestration frameworks and interoperability protocols such as MCP and ACP
Experience designing and operating CI/CD pipelines, infrastructure-as-code, artifact management, and containerized deployment environments using technologies such as Kubernetes, Terraform,ArgoCD, Artifactory, Jenkins, Git, or equivalent tools
Strong Linux administration skills, including troubleshooting, log analysis, system diagnostics, SSH, certificates, security fundamentals, and automation using languages such as Python, Go, Groovy, or similar
Experience integrating monitoring and observability solutions using tools such as Grafana, OpenSearch, Prometheus,InfluxDB, Zabbix, or equivalent technologies
Experience integrating third-party services and APIs, including REST-based integrations, within Linux-based environments
Ability to work independently, solve ambiguous technical problems, collaborate across teams, and translate business workflows into scalable technical solutions