Jithin Sasikumar Email & Phone Number

Bonn, Nrw, De

Sankt Augustin, North Rhine-Westphalia, Germany

𝗖𝗼𝗻𝘃𝗲𝗿𝗴𝗲𝗻𝗰𝗲 𝗼𝗳 𝗛𝗣𝗖 𝘄𝗶𝘁𝗵 𝗞𝘂𝗯𝗲𝗿𝗻𝗲𝘁𝗲𝘀 𝘁𝗼 𝗱𝗲𝗽𝗹𝗼𝘆 𝗮 𝘀𝗰𝗮𝗹𝗮𝗯𝗹𝗲 𝗠𝗟𝗢𝗽𝘀 𝗽𝗹𝗮𝘁𝗳𝗼𝗿𝗺✔ Researching and implementing methods to converge High-Performance Computing (HPC) with Kubernetes, enhancing the MLOps platform to support both HPC and non-HPC tasks, and making it suitable for research and production.✔ Experimenting with an end-to-end MLOps pipeline, including distributed multi-node GPU training, deployment, inference and CI/CD.✔… Show more 𝗖𝗼𝗻𝘃𝗲𝗿𝗴𝗲𝗻𝗰𝗲 𝗼𝗳 𝗛𝗣𝗖 𝘄𝗶𝘁𝗵 𝗞𝘂𝗯𝗲𝗿𝗻𝗲𝘁𝗲𝘀 𝘁𝗼 𝗱𝗲𝗽𝗹𝗼𝘆 𝗮 𝘀𝗰𝗮𝗹𝗮𝗯𝗹𝗲 𝗠𝗟𝗢𝗽𝘀 𝗽𝗹𝗮𝘁𝗳𝗼𝗿𝗺✔ Researching and implementing methods to converge High-Performance Computing (HPC) with Kubernetes, enhancing the MLOps platform to support both HPC and non-HPC tasks, and making it suitable for research and production.✔ Experimenting with an end-to-end MLOps pipeline, including distributed multi-node GPU training, deployment, inference and CI/CD.✔ 𝗧𝗲𝗰𝗵 𝗦𝘁𝗮𝗰𝗸: Kubernetes, Slurm, Kubeflow, Python, Ansible, MLflow, Istio, Pytorch, MinIO, Longhorn, Prometheus, Grafana, Linux Show less

North Rhine-Westphalia, Germany

𝗠𝗟𝗢𝗽𝘀: ✔ Developed and managed a highly-available Kubernetes (K8s) cluster in the Fraunhofer cloud. ✔Deployed and maintained an on-premise scalable MLOps platform on Kubernetes using the full Kubeflow suite. ✔ Deployed an MLflow server to track model training experiments and manage model registry for the MLOps platform serving various environments, including development and production. ✔ Prototyped the migration of the ASR model training pipeline to the K8s… Show more 𝗠𝗟𝗢𝗽𝘀: ✔ Developed and managed a highly-available Kubernetes (K8s) cluster in the Fraunhofer cloud. ✔Deployed and maintained an on-premise scalable MLOps platform on Kubernetes using the full Kubeflow suite. ✔ Deployed an MLflow server to track model training experiments and manage model registry for the MLOps platform serving various environments, including development and production. ✔ Prototyped the migration of the ASR model training pipeline to the K8s cluster and utilized Apache Airflow for automation, significantly streamlining the training process. ✔ Automated the management of the Kubernetes cluster with Ansible, streamlining operations and enhancing efficiency. ✔ Converted legacy Python scripts for various language model training tasks into Groovy, enhancing build automation with Gradle. ✔ 𝗧𝗲𝗰𝗵 𝗦𝘁𝗮𝗰𝗸: Python, Kubernetes, Kubeflow, Airflow, Ansible, Helm, Bash, Prometheus, Grafana, Gradle, Groovy𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵: ✔ Conducted research on federated learning approaches for keyword spotting tasks achieving comparable performance to traditional algorithms on a GPU cluster, while enhancing data privacy. ✔ 𝗠𝗟/𝗗𝗟 𝗳𝗿𝗮𝗺𝗲𝘄𝗼𝗿𝗸𝘀: Tensorflow, Tensorflow Federated, Keras, Pytorch, Pysyft Show less

Cologne, North Rhine-Westphalia, Germany

𝗘𝘅𝗽𝗹𝗮𝗶𝗻𝗶𝗻𝗴 𝗱𝗲𝗲𝗽 𝗹𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗺𝗼𝗱𝗲𝗹𝘀 𝗳𝗼𝗿 𝗱𝗲𝘁𝗲𝗰𝘁𝗶𝗻𝗴 𝗮𝗻𝗼𝗺𝗮𝗹𝗶𝗲𝘀 𝗶𝗻 𝘁𝗶𝗺𝗲-𝘀𝗲𝗿𝗶𝗲𝘀 𝗱𝗮𝘁𝗮 (𝗥&𝗗 𝗣𝗿𝗼𝗷𝗲𝗰𝘁)✔ Proposed a best-fit method that generates explanations for a deep neural network by comparing the existing approaches to explain the decisions of models trained on time-series data (specifically satellite telemetry data).✔ The proposed approach focuses on explaining LSTM networks for anomaly detection tasks.✔… Show more 𝗘𝘅𝗽𝗹𝗮𝗶𝗻𝗶𝗻𝗴 𝗱𝗲𝗲𝗽 𝗹𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗺𝗼𝗱𝗲𝗹𝘀 𝗳𝗼𝗿 𝗱𝗲𝘁𝗲𝗰𝘁𝗶𝗻𝗴 𝗮𝗻𝗼𝗺𝗮𝗹𝗶𝗲𝘀 𝗶𝗻 𝘁𝗶𝗺𝗲-𝘀𝗲𝗿𝗶𝗲𝘀 𝗱𝗮𝘁𝗮 (𝗥&𝗗 𝗣𝗿𝗼𝗷𝗲𝗰𝘁)✔ Proposed a best-fit method that generates explanations for a deep neural network by comparing the existing approaches to explain the decisions of models trained on time-series data (specifically satellite telemetry data).✔ The proposed approach focuses on explaining LSTM networks for anomaly detection tasks.✔ 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝘁𝗼𝗽𝗶𝗰𝘀: Deep Learning, Deep Neural Networks, LSTM, Explainable AI (XAI), Feature Importance, Satellite Telemetry, Anomaly Detection, Time-series. If interested, please feel free to check out the project 👉@ https://github.com/Jithsaavvy/Explaining-deep-learning-models-for-detecting-anomalies-in-time-series-data-RnD-project Show less

Chennai Area, India

Amazon Alexa AI @ Amazon Development Center✔ Machine Learning✔ Natural Language Understanding [NLU] - Based on Ontologies & Knowledge graphs✔ Contextual and Semantic Analysis

Chennai Area, India

- Networking- Routing - TCP/IP

Chennai Area, India

SEO with eCommerce

Master Of Science - Ms, Autonomous Systems

𝗠𝗮𝗷𝗼𝗿 𝗦𝗽𝗲𝗰𝗶𝗮𝗹𝗶𝘇𝗮𝘁𝗶𝗼𝗻: AI, Machine learning, Deep learning 𝗥𝗲𝗹𝗲𝘃𝗮𝗻𝘁 𝗖𝗼𝘂𝗿𝘀𝗲𝘄𝗼𝗿𝗸: ✔ Advanced Software Technology ✔ Machine Learning ✔ Natural.

Bachelor Of Engineering (B.E), Computer Science And Engineering

Activities and Societies: Coding Contests, TCS Codevita, Symposiums, ACM-ICPC 𝗥𝗲𝗹𝗲𝘃𝗮𝗻𝘁 𝗖𝗼𝘂𝗿𝘀𝗲𝘄𝗼𝗿𝗸: ✔ Programming and Data Structures - I &.