Job Summary
Key Responsibilities
2. Troubleshoot and resolve bugs in ML pipelines leveraging Apache Spark and Kafka, supporting data ingestion and transformation tasks.
3. Support model evaluation by applying cross-validation, ROC/AUC, Precision/Recall, F1-score, and confusion matrix techniques to assess performance of supervised learning models.
4. Participate in team code reviews and contribute to documentation of ML workflows and client deliverables using Python and ML libraries.
5. Monitor and process data streams for forecasting tasks using Apache Kafka and Spark, assisting in scheduled delivery and reporting of results.
6. Collaborate with team members to gather requirements and present forecasting results, supporting day-to-day client requests and ticket resolution.
Skill Requirements
2. Experience With Python Programming And Libraries Such As Numpy, Pandas, Scikitlearn, Tensorflow, And Pytorch.
3. Good Knowledge Of Time Series Analysis And Forecasting Techniques Using Statsmodels And Related Tools.
4. Familiarity With Data Engineering Platforms Including Apache Spark And Kafka For Processing And Managing Large Datasets.
5. Ability To Apply Model Evaluation Metrics Including Crossvalidation, Roc/Auc, Precision/Recall, F1Score, And Confusion Matrix.
6. Experience With Supervised And Unsupervised Learning Approaches.
7. Good Documentation And Communication Skills For Presenting Results And Supporting Client Requirements.
Other Requirements
2. - Microsoft Certified: Azure Ai Fundamentals
3. - Tensorflow Developer Certificate
4. - Databricks Certified Associate Developer For Apache Spar