AI/ML Engineer

As a Data Scientist at Lifease Solutions LLP, your main responsibility will be to develop machine learning and deep learning models for predicting match scores & outcomes, team & player performances, and statistics. You will also be involved in in-depth cricket analytics to analyze player form, team strengths, matchups, and opposition weaknesses. Additionally, you will work on data processing & engineering tasks, model deployment & MLOps, and performance metrics & model explainability. Key Responsibilities: - Develop ML/DL models for predicting match scores & outcomes, team & player performances, and statistics. - Implement time-series forecasting models (LSTMs, Transformers, ARIMA, etc.) for score predictions. - Train and fine-tune reinforcement learning models for strategic cricket decision-making. - Develop ensemble learning techniques to improve predictive accuracy. - Design models to analyze player form, team strengths, matchups, and opposition weaknesses. - Build player impact and performance forecasting models based on pitch conditions, opposition, and recent form. - Extract insights from match footage and live tracking data using deep learning-based video analytics. - Collect, clean, and preprocess structured and unstructured cricket datasets from APIs, scorecards, and video feeds. - Build data pipelines (ETL) for real-time and historical data ingestion. - Work with large-scale datasets using big data tools (Spark, Hadoop, Dask, etc.). - Deploy ML/DL models into production environments (AWS, GCP, Azure etc). - Develop APIs to serve predictive models for real-time applications. - Implement CI/CD pipelines, model monitoring, and retraining workflows for continuous improvement. - Define and optimize evaluation metrics (MAE, RMSE, ROC-AUC, etc.) for model performance tracking. - Implement explainable AI techniques to improve model transparency. - Continuously update models with new match data, player form & injuries, and team form changes. Qualification Required: - Bachelor's or Master's degree in Computer Science, Statistics, Mathematics, or a related field. - Strong experience in predictive modeling, deep learning, and data analytics. - Proficiency in Python programming and relevant libraries (e.g., TensorFlow, PyTorch, scikit-learn). - Experience with big data tools such as Spark, Hadoop, or Dask. - Knowledge of cloud platforms like AWS, GCP, or Azure for model deployment. - Excellent communication and collaboration skills to work in a team environment.,