DevOps, MLOps & Oracle Database Administrator | MSc Computer Science | Machine Learning Researcher

Focused on building reliable, observable ML systems end-to-end: from data and training to deployment and monitoring on Azure/AWS with Kubernetes and CI/CD.

• Current roles: DevOps Engineer | Oracle Database Administrator | MLOps
• Previous role: Application Support Engineer

I'm a DevOps and MLOps engineer with hands-on Oracle database administration experience. My research and project interests include Automatic Speech Recognition (ASR) for Ghanaian languages, CNN-based computer vision, and accessible AI. I build reliable ML services and cloud-native platforms, automate workflows, and productionize models with testing, security, and observability. On the database side, I focus on performance, resilience, and automation in Oracle environments.

• CNN model for image classification in Akan Twi
• ASR for Ghanaian languages and accessibility use cases
• Scalable cloud infrastructure and CI/CD for ML services

• Advanced cloud infrastructure: Azure, AWS, Kubernetes, CI/CD
• MLOps: training pipelines, testing, packaging, serving, monitoring
• Federated learning for privacy-preserving healthcare ML

• Cloud & DevOps: Azure, AWS, CI/CD, Kubernetes, Docker, Vagrant
• MLOps: pipelines, model packaging/serving, monitoring, drift detection
• Oracle DBA: RMAN backup/recovery, performance tuning (AWR/ASH), Data Guard
• Data Engineering: SQL/NoSQL data pipelines and validation

• LinkedIn: https://www.linkedin.com/in/joseph-adeleke-27b433149/
• Email: [email protected]
• GitHub: https://github.com/jadeleke

• Reproducible training: versioned data, pipelines, and rigorous evaluation
• CI/CD for ML: unit/integration tests, containerization, environment promotion
• Model serving: REST/gRPC inference on Docker/Kubernetes with autoscaling
• Observability: metrics, logs, and tracing with Grafana, Elasticsearch, Datadog
• Governance: experiment tracking, model comparison, and release discipline

• Oracle administration: backup/recovery (RMAN), HA/DR (Data Guard), patching
• Performance: SQL tuning, indexing/partitioning, AWR/ASH analysis
• Automation: PL/SQL, SQL*Plus, Bash/PowerShell, scheduled jobs
• Schema change management: repeatable migrations (Liquibase/Flyway)
• Monitoring: OEM/Cloud Control, Grafana/Prometheus, Datadog alerts

• MLOps: MLflow (tracking/registry), DVC (data/versioning), Prefect/Airflow (orchestration), Kubeflow (pipelines), KServe/Triton (serving), FastAPI (inference APIs)
• Data: Pandas/Polars, PySpark, Great Expectations (validation)
• DB Change Mgmt: Liquibase/Flyway (repeatable migrations, drift detection)

• Focused on CI/CD, containerization, and cloud-native deployments on Azure/AWS
• Emphasis on reliability, security, and observability for applications and ML services

• Managed Oracle databases with RMAN backup/recovery and automated maintenance
• Tuned performance using AWR/ASH, optimized SQL, indexes, and partitioning
• Implemented HA/DR with Data Guard; coordinated patching and upgrades
• Automated DBA tasks using PL/SQL, SQL*Plus, Bash/PowerShell
• Integrated database monitoring with OEM/Cloud Control, Grafana, and Datadog

• Ensured system reliability via functional regression testing and performance tuning
• Provided technical assistance to internal/external teams; triaged and resolved defects
• Wrote SQL for data validation during testing and troubleshooting
• Built and customized Grafana dashboards for real-time monitoring
• Leveraged Datadog for performance analysis and proactive bottleneck resolution
• Automated repetitive tasks with Bash to improve efficiency and reduce errors

• Language Detection for Ghanaian Languages - lightweight NLP for low-resource contexts repo | demo
• CNN Image Classification in Akan Twi - dataset curation and supervised training repo | demo
• ASR for Speech Impairments in Twi - accessibility-focused speech recognition repo | demo
• SMS Spam Detection in Swahili - classical ML pipeline from EDA to deployment repo | demo
• Brain Tumor Classification with Federated Learning - privacy-preserving model training repo | demo

flowchart LR
  A[Data Sources] --> B[Ingestion & Validation]
  B --> C[Feature Engineering]
  C --> D[Train & Evaluate]
  D --> E[Model Registry]
  E --> F[CI/CD: Build / Test / Scan]
  F --> G[Containerize & Deploy]
  G --> H[Online Serving: REST and gRPC]
  H --> I[Monitoring & Logging]
  I --> J[Drift Detection & Alerts]
  J --> D

Turning AI research into reliable, real-world systems.