Cross-domain technical leverage
Connects legacy and modern telecom operations with data engineering, observability, automation, database platforms and AI/MLOps practices.
Profile
About
I operate at the intersection of critical telecom operations, data engineering, observability and AI enablement. With 25+ years of experience in Voice/Core networks, I help transform complex operational environments into more reliable, measurable and automated platforms.
My work spans IMS/SDVoice support, PostgreSQL/TimescaleDB and MySQL-based monitoring environments, Grafana Enterprise operations, Python ETL pipelines, KPI engineering, vulnerability and patch lifecycle management, and ML/AI training. The common thread is not the number of technologies, but the ability to connect them into practical capabilities that reduce operational risk, improve visibility and enable teams to act faster.
Principal Value Proposition
Cross-team technical leverage, not just individual execution
Operational platform thinking
Builds reusable capabilities, monitoring foundations, data pipelines and support models used by multiple teams rather than isolated one-off scripts.
End-to-end ownership
Supports critical capabilities across OS, databases, dashboards, integrations, users, patching, upgrades, vulnerabilities and operational support.
Metrics into decisions
Transforms raw Voice network measurements into structured KPIs, dashboards, aggregations and actionable operational intelligence.
Reduced escalation dependency
Solves complex Grafana, database, Linux and monitoring issues internally whenever possible, reducing delays and vendor dependency.
Team enablement
Shares knowledge through training, technical guidance, hands-on support, documentation and ML/AI education for colleagues.
Core Pillars
One mission, multiple technical foundations
Telecom Domain Authority
Deep Voice/Core network expertise across IMS, SDVoice, SIP/Diameter, core applications, access, roaming, alarms and operational troubleshooting.
Observability & Operational Intelligence
Design and support of monitoring platforms, Grafana Enterprise dashboards, KPI models and near real-time visibility for critical network operations.
Data Engineering & Platform Reliability
Python ETL, PostgreSQL/TimescaleDB, MySQL 8, metric normalization, storage, aggregation, analysis, upgrades, patching and vulnerability handling.
MLOps & AI Enablement
Contribution to MLOps initiatives, anomaly detection concepts, AI-assisted operational workflows and practical ML/AI training adoption.
Platforms & Projects
Selected operational capabilities
Platform Ownership / Secure Operations
dev-ngns Platform: Databases, Microservices & Secure Operations
Operational ownership and support of a complex dev-ngns environment with PostgreSQL + TimescaleDB, MySQL 8, 45+ microservices and Rocky/RHEL Linux 8 systems. Responsibilities include database design and creation, support for other teams using the databases, upgrades, patch fixes, vulnerability handling and secure operations.
Impact: Improves reliability, patch readiness, security posture and database usability for multiple internal teams.
Observability Platform
Network Awareness & Grafana Enterprise Operations
Administration and support of the network-awareness environment, including local MySQL 8 database, Grafana Enterprise, dashboards, plugins, patching, upgrades, vulnerability handling, user administration and support for 420+ users.
Impact: Enables reliable observability for voice-network operations and resolves many Grafana-related issues internally before vendor escalation is required.
Data Engineering / Operational Intelligence
Voice Network Metrics to KPIs
Python programs for ETL, data organization, metric aggregation, KPI calculation, storage and analysis across Voice access, IMS, Core, application servers, roaming, alarms and related operational measurements.
Impact: Transforms raw operational measurements into structured insights that support faster troubleshooting, proactive monitoring and management reporting.
Proactive Operations / Network Readiness
Emergency Events & Network Impact Monitoring
Near real-time monitoring concept and implementation for public emergency events in Greece, including 112 alerts, severe weather, earthquakes and fires, correlated with potentially affected network elements.
Impact: Strengthens operational readiness by enabling faster risk identification, faster response and better customer-impact reduction.
MLOps / Telecom Monitoring
SDVoice Automatic Monitoring with Anomaly Detection
Technical proposal and direction for SDVoice monitoring with anomaly detection, combining telecom domain knowledge, metrics, monitoring pipelines and ML-oriented analysis.
Impact: Moves operational monitoring toward proactive fault detection and intelligent network assurance.
AI Enablement / Training
ML & AI Essentials Training Program
Co-designed and delivered the ML & AI Essentials program with OTEAcademy and the instructor team, covering practical ML/AI fundamentals and organizational enablement.
Impact: Supports digital upskilling across the organization with excellent participant feedback and strong demand for further training expansion.
Career
Experience
ML & AI Instructor
OTEAcademy
- Member of the instructor team that designed and launched the ML & AI Essentials training program.
- Deliver practical ML/AI fundamentals with a strong focus on real business and operational use cases.
- Contribute to content evolution and preparation of advanced training paths, maintaining consistently excellent participant feedback.
Data Science & MLOps Engineer
OTE Group of Companies (HTO) - NT MLOps & AI Squad
- Design and support ML/MLOps-oriented solutions from technical analysis to deployment and monitoring.
- Develop Python automation, ETL, data pipelines, data normalization, aggregation and KPI-oriented analytics for network operations.
- Support squad initiatives with Linux, databases, microservices, architecture and workflow expertise.
Senior Voice Support Engineer
OTE Group of Companies (HTO)
- Support Huawei IMS and Nokia SDVoice voice-core environments, including Core, SBC, HSS, MGW, application servers, roaming and alarms.
- Handle incidents, SRs, OCT/CTT/NTT tickets and migration-related issues with strong SLA performance and customer-impact focus.
- Build monitoring, automation, dashboards and analytics that improve troubleshooting, reduce MTTR and enhance operational readiness.