SaiJyothi Yalamuri

• Designed, developed, and deployed AI-driven cloud solutions leveraging AWS, Azure, and Kubernetes-based environments.
• Built, containerized, and orchestrated AI microservices using Docker, OpenShift, and Helm, ensuring scalable and reliable deployment pipelines.
• Created and managed APIs and data pipelines to support AI models and cloud-native applications, integrating data ingestion, preprocessing, and inference services.
• Implemented Infrastructure-as-Code (IaC) using Terraform and Ansible to automate provisioning and configuration of AI workloads across hybrid clouds.
• Integrated CI/CD pipelines with GitOps and ArgoCD to enable continuous delivery and rapid iteration of AI applications.
• Monitored and optimized AI model performance using Prometheus, Grafana, and OpenSearch, ensuring efficiency and cost optimization in production.
• Deployed AI inference services at scale using containerized and serverless architectures, improving latency and reliability.
• Collaborated with data science and engineering teams to operationalize AI models, enabling seamless model versioning, validation, and rollout.
• Applied best practices in cloud security, observability, and scalability for AI systems handling large data volumes and real-time workloads.
• Documented architectures, deployment workflows, and APIs, ensuring clarity and knowledge continuity across teams.

● Provided 24x7 NOC support for critical infrastructure services spanning on-premises data centers and cloud-hosted environments (AWS, Azure, VMware), ensuring uninterrupted service delivery for enterprise clients.

● Performed continuous infrastructure health checks, monitoring the performance and availability of servers, storage systems, network switches, firewalls, and containerized applications on RedHat OpenShift.

● Utilized Prometheus, Grafana, OneConsole, and CloudWatch to track system KPIs such as CPU utilization, memory usage, disk I/O, network throughput, and latency, ensuring that thresholds were met at all times.

● Acknowledged and validated alerts generated by the monitoring systems, filtering out false positives, prioritizing critical incidents, and assigning them to the appropriate Tier 2/Tier 3 support teams.

● Conducted initial triage on infrastructure faults, including log analysis, port checks, pod/VM restarts, configuration validation, and verifying connectivity between core components.

● Documented each incident thoroughly in ServiceNow, including impact statements, RCA summaries, escalation notes, and resolution timelines for compliance and future reference.

● Utilized Prometheus, Grafana, and OneConsole for real-time service health monitoring, KPI tracking, and capacity utilization analysis.

● Executed operational tasks including pod restarts, basic configuration checks, and L1/L2 runbook executions for fault remediation.

● Ensured stability and performance of Virtual Network Functions such as EPC, IMS, PCRF, and VoLTE core elements.

● Worked closely with RAN, transport, and core network teams to validate end-to-end service readiness for 5G trials and production rollout.

● Configured Multus CNI in OpenShift for multiple network interfaces per CNF to support control plane and user plane separation in 5G deployments.

● Tuned worker nodes for NUMA-aware CPU pinning, hugepages allocation, and interface bonding to meet 5G Core throughput requirements.

● Oversaw the health and performance of core network functions and containerized applications running on RedHat and VMware hybrid cloud platforms.

● Diagnosed and resolved IP-based and wireless core network issues across MSC, HLR/HSS, SGSN/MME, and GGSN/PGW elements.

● Supported deployment, integration, and acceptance testing of 4G and early 5G trial sites, including eNodeB and gNodeB activations.

● Conducted Location Routing Number (LRN) migrations, BSC additions/removals, and implemented changes through controlled CR processes.

● Configured APNs, bearer profiles, CAMEL settings, SGSN/GGSN, and LTE packet core parameters for data services.

● Performed roaming configuration audits and end-to-end voice/SMS/data testing for domestic and international roaming partners.

● Served as the primary contact for high-severity incidents, performing root cause isolation through log analysis, symptom matching, and KPI correlation.

● Documented incidents in ServiceNow, ensured proper impact classification, and coordinated escalations to Tier 3/vendor teams (Ericsson, Nokia, Cisco, RedHat).

● Worked closely with the NOC to reduce Mean Time to Repair by streamlining triage and escalation procedures.

● Provided L2 support for VIP customers, resolving persistent roaming, call quality, and data service issues.

● Integrated 5G Core CNFs with Prometheus, and Instana for full-stack observability, enabling proactive fault detection.

● Performed root-cause analysis of signaling and bearer path failures by correlating metrics, logs, and packet captures (using tcpdump, Wireshark).

● Monitored KPI dashboards to identify trends in service degradation, proactively initiating corrective actions to prevent outages.

● Tuned QoS parameters and optimized neighbor lists for LTE/4G to improve network accessibility and handover success rates.

● Generated daily/weekly health reports, traffic analytics, and RCA documentation for leadership review.

● Contributed to continuous improvement initiatives by recommending alert threshold refinements and enhancing monitoring logic to reduce false positives.

• Developed a face mask detection system using CNN and ResNet-50, achieving 94% accuracy with TensorFlow.
• Created a full-stack online learning management platform with role-based access to enhance user experience.
• Collaborated with a dynamic team at SmartKnower, a startup focused on innovative AI solutions in Hyderabad.