Meerasa Shaik Chennupalli

Dynamic DevOps Engineer with expertise in automating CI/CD pipelines and containerization. Strong background in machine learning applications for predictive analysis, driving operational efficiency and cost savings through innovative cloud solutions.

Hacker Rank Issued Jan 2023Issued Jan 2023Credential ID 5979087073D3Credential ID 5979087073D3Implementing Data Models and Reports with Microsoft SQL Server Implementing Data Models and Reports with Microsoft SQL Server

• Skills: CRUD · Database Queries · Relational Data Modeling · Optimization · Data Storage Technologies · Normalization

Advanced python programming

BRAINOVISION SOLUTIONS INDIA PVT.LTDBRAINOVISION SOLUTIONS INDIA PVT.LTDIssued Sep 2022

UdemyUdemyIssued Sep 2022Issued Sep 2022Credential ID UC-6e2486bd-b356-48c3-979b-318526e50e41Credential ID UC-6e2486bd-b356-48c3-979b-318526e50e41
MTA: Introduction to Programming Using PythonMTA: Introduction to Programming Using Python

• Skills: oops · Data handling · Python (Programming Language)

Udemy Issued Sep 2022Credential ID UC-6e2486bd-b356-48c3-979b-318526e50e41Credential ID UC-6e2486bd-b356-48c3-979b-318526e50e41MTA: Introduction to Programming Using PythonMTA: Introduction to Programming Using Python

• Skills: oops · Data handling · Python (Programming Language)

Udemy Issued Jul 2022Credential ID 486bd-b356-48c3-979b-318526e50e41Credential ID 486bd-b356-48c3-979b-318526e50e41
C++ programming

• Skills: Object-Oriented Programming (OOP) · C++ · Debugging · Standard Template Library (STL)

• Built custom datasets with annotation (LabelImg), preprocessing, and augmentation for robustness.
  
  Implemented TensorFlow Object Detection API pipelines with TFRecords, hyperparameter tuning, and evaluation.
  
  Learned model performance metrics (mAP, IoU, Precision-Recall) and handled small-object detection challenges.
  
  Optimized models for edge deployment (FPS ~20,
  Gained experience in error analysis (confusion matrices, class imbalance) and applied mitigation strategies.
  
  Designed scalable deployment workflows with integration to IoT/surveillance systems for real-world use

• Conducted network protocol analysis by comparing TCP variants (Reno, CUBIC, BBR) with QUIC.
  
  Designed and simulated custom Mininet network topologies (dumbbell) with controlled bandwidth, delay, and packet loss.
  
  Implemented TCP testing with iperf3 and QUIC testing with aioquic under identical conditions.
  
  Automated experiments with Python scripts for reproducibility and logging of results.
  
  Measured and analyzed throughput, latency, and packet recovery efficiency across protocols.
  
  Gained hands-on expertise in Linux traffic control (tc, netem) for emulating real-world conditions.
  
  Identified BBR as the most efficient TCP variant and evaluated QUIC’s strengths/limitations in lossy networks

• Designed and implemented Spatio-Temporal Convolutional Networks (STCNs) for real-time anomaly detection.
  
  Preprocessed video datasets (frame extraction, resizing, labeling) for deep learning tasks.
  
  Applied 3D CNNs with temporal convolutions to capture motion patterns and spatial features.
  
  Built and compared baseline autoencoder models with STCNs, optimizing thresholds for anomaly detection.
  
  Evaluated models using accuracy, precision, recall, F1-score, ROC-AUC, and confusion matrices.
  
  Gained hands-on experience with PyTorch for deep learning implementation.
  
  Improved anomaly detection accuracy (>95%) on crime surveillance datasets

• Developed end-to-end monitoring pipelines using Prometheus, Grafana, kube-state-metrics, and cAdvisor.
  
  Built real-time dashboards for pod/node CPU & memory utilization, underutilized nodes, and workload inefficiencies.
  
  Applied time-series forecasting with scikit-learn (Linear Regression) for predictive right-sizing and cost savings.
  
  Designed YAML-based Kubernetes manifests for transparent, GitOps-compatible deployments.
  
  Implemented data collection and metric reconciliation strategies across KSM & cAdvisor.
  
  Gained hands-on expertise in observability, anomaly detection, and performance tuning at cluster scale.
  
  Explored future enhancements like LSTM-based ML models, SLA dashboards, and multi-cluster federation