Machine Learning Engineer - Python

Key Responsibilities :

• Develop Machine Learning Models : Design, build, and deploy machine learning models using Python, focusing on predictive and prescriptive analytics, with an emphasis on time series forecasting.
• Time Series Analysis : Apply advanced time series techniques (e.g., ARIMA, SARIMA, Prophet, LSTM) to analyze temporal data and generate accurate forecasts for business applications.
• Data Extraction and Manipulation : Write complex SQL queries to extract, transform, and analyze large datasets from relational databases, ensuring data integrity and efficiency.
• Model Productionization : Implement end-to-end machine learning pipelines, including model training, validation, deployment, and monitoring, using MLOps practices to ensure scalability and reliability in production environments.
• Data Exploration and Visualization : Conduct exploratory data analysis (EDA) and create insightful visualizations using Python libraries (e.g., Matplotlib, Seaborn, Plotly) to communicate findings to stakeholders.
• Collaboration : Work closely with cross-functional teams, including engineers, product managers, and business analysts, to align data science solutions with business needs and integrate models into operational systems.
• Performance Optimization : Monitor and optimize model performance in production, addressing issues like drift, bias, or scalability, and iterate on models to improve accuracy and efficiency.
• Documentation and Reporting : Document methodologies, model performance, and insights clearly, and present findings to technical and non-technical audiences to drive Capabilities :
• Programming Languages : Advanced proficiency in Python for data analysis, machine learning, and scripting (e.g., Pandas, NumPy, scikit-learn, TensorFlow, PyTorch).
• SQL Expertise : Strong ability to write efficient SQL queries for data extraction, transformation, and analysis in relational databases (e.g., PostgreSQL, Snowflake, or similar).
• Machine Learning : Extensive experience in building, evaluating, and deploying machine learning models, including supervised and unsupervised learning techniques.
• Time Series Analysis : Deep expertise in time series forecasting methods (e.g., ARIMA, SARIMA, ETS, Prophet, RNNs / LSTMs) and handling temporal data challenges like seasonality and trend analysis.
• MLOps and Deployment : Familiarity with productionizing machine learning models using tools like MLflow, Kubeflow, or cloud-based platforms (e.g., AWS SageMaker, Azure ML, Google Cloud AI Platform).
• Data Visualization : Proficiency in creating impactful visualizations using Python libraries (e.g., Matplotlib, Seaborn, Plotly) or BI tools (e.g., Spotfire, Power BI).
• Version Control : Experience with Git or similar version control systems for collaborative development and model versioning.
• Cloud Technologies : Knowledge of cloud platforms (AWS, Azure, Google Cloud) for data storage, processing, and model deployment is a plus.

(ref : hirist.tech)