• Designs, implements, and continuously improves observability strategies across services, including metrics, logs, traces, alerts, and dashboards. • Focuses on understanding system behavior in production, identifying failure modes, performance bottlenecks, and reliability risks. • Evolves and maintains shared AWS CDK and CDK8s constructs, with emphasis on observability, autoscaling, and operational safeguards rather than basic infrastructure provisioning. • Maintains and operates core platform components such as VPC, EKS clusters, RDS, OpenSearch, and MSK, ensuring they expose meaningful operational signals. • Operates and enhances Kubernetes cluster addons such as ingress controllers, cert-manager, autoscalers, and monitoring, logging, and tracing stacks. • Defines and maintains SLIs, SLOs, and alerting strategies that clearly distinguish between symptoms, root causes, and actionable operational events. • Improves automated operational responses, including autoscaling, self-healing mechanisms, and runbook-driven remediation. • Ensures high reliability through structured alerting systems (Prometheus, CloudWatch), noise reduction, alert quality improvements, and recovery mechanisms. • Collaborates with engineering teams to investigate production incidents, perform root cause analysis, and drive long-term reliability improvements. • Owns CI/CD pipelines for Infrastructure as Code (IaC) and observability-related platform components. • Applies Site Reliability Engineering (SRE) principles—including observability-first design, error budgets, and operational readiness—to shared platform services. • Supports IAM roles, secrets management, and tenant isolation best practices.

• Designs, implements, and continuously improves observability strategies across services, including metrics, logs, traces, alerts, and dashboards. • Focuses on understanding system behavior in production, identifying failure modes, performance bottlenecks, and reliability risks. • Evolves and maintains shared AWS CDK and CDK8s constructs, with emphasis on observability, autoscaling, and operational safeguards rather than basic infrastructure provisioning. • Maintains and operates core platform components such as VPC, EKS clusters, RDS, OpenSearch, and MSK, ensuring they expose meaningful operational signals. • Operates and enhances Kubernetes cluster addons such as ingress controllers, cert-manager, autoscalers, and monitoring, logging, and tracing stacks. • Defines and maintains SLIs, SLOs, and alerting strategies that clearly distinguish between symptoms, root causes, and actionable operational events. • Improves automated operational responses, including autoscaling, self-healing mechanisms, and runbook-driven remediation. • Ensures high reliability through structured alerting systems (Prometheus, CloudWatch), noise reduction, alert quality improvements, and recovery mechanisms. • Collaborates with engineering teams to investigate production incidents, perform root cause analysis, and drive long-term reliability improvements. • Owns CI/CD pipelines for Infrastructure as Code (IaC) and observability-related platform components. • Applies Site Reliability Engineering (SRE) principles—including observability-first design, error budgets, and operational readiness—to shared platform services. • Supports IAM roles, secrets management, and tenant isolation best practices.

• Designs, implements, and continuously improves observability strategies across services, including metrics, logs, traces, alerts, and dashboards. • Focuses on understanding system behavior in production, identifying failure modes, performance bottlenecks, and reliability risks. • Evolves and maintains shared AWS CDK and CDK8s constructs, with emphasis on observability, autoscaling, and operational safeguards rather than basic infrastructure provisioning. • Maintains and operates core platform components such as VPC, EKS clusters, RDS, OpenSearch, and MSK, ensuring they expose meaningful operational signals. • Operates and enhances Kubernetes cluster addons such as ingress controllers, cert-manager, autoscalers, and monitoring, logging, and tracing stacks. • Defines and maintains SLIs, SLOs, and alerting strategies that clearly distinguish between symptoms, root causes, and actionable operational events. • Improves automated operational responses, including autoscaling, self-healing mechanisms, and runbook-driven remediation. • Ensures high reliability through structured alerting systems (Prometheus, CloudWatch), noise reduction, alert quality improvements, and recovery mechanisms. • Collaborates with engineering teams to investigate production incidents, perform root cause analysis, and drive long-term reliability improvements. • Owns CI/CD pipelines for Infrastructure as Code (IaC) and observability-related platform components. • Applies Site Reliability Engineering (SRE) principles – including observability-first design, error budgets, and operational readiness – to shared platform services. • Supports IAM roles, secrets management, and tenant isolation best practices.

• Embed directly with clients to design, build, and deploy custom AI solutions and autonomous LLM-based agents tailored to their specific business needs. • Integrate AI capabilities into existing software development life cycles (SDLC) and core business processes to streamline workflows and drive measurable efficiency. • Troubleshoot, debug, and maintain models within production environments to ensure long-term reliability, performance, and scalability. • Translate high-fidelity customer insights and real-world technical challenges into actionable feedback for internal product and engineering teams to help shape the OpenAI roadmap. • Develop and share best practices for LLM implementation to help partners and the broader developer community scale their AI initiatives effectively.