ML / Data Engineer

• The ideal candidate thrives on building, deploying, and maintaining ML solutions that deliver measurable business impact.
• While the primary focus is on ML model development, deployment, and monitoring, experience in data engineeringespecially in handling large, complex datasetsis a strong plus.
• Key Responsibilities Model Development & Deployment Design, build, and deploy machine learning models using Python (Pandas, NumPy, scikit-learn, TensorFlow, PyTorch).
• Time Series Forecasting Apply advanced time series techniques (ARIMA, SARIMA, Prophet, LSTM/RNNs) to forecast and model temporal data.
• MLOps Build and manage ML pipelines for training, validation, deployment, and monitoring using tools like MLflow, Kubeflow, or cloud-based ML services.
• Model Monitoring & Optimization Track performance, detect drift or bias, and iterate on models to improve accuracy, reliability, and scalability.
• Feature Engineering Develop and select impactful features, especially for time series and structured datasets.
• Exploratory Data Analysis & Visualization Analyze datasets and communicate findings through clear visualizations (Matplotlib, Seaborn, Plotly) to guide decision-making.
• Collaboration Work with product managers, data scientists, engineers, and business stakeholders to align ML solutions with real-world needs.
• (Bonus) Data Engineering If you have strong SQL and ETL skills, help design and optimize data pipelines to ensure models have clean, reliable inputs.
• Required Skills Advanced Python programming for ML (Pandas, NumPy, scikit-learn, TensorFlow, or PyTorch).
• Strong understanding of supervised, unsupervised, and deep learning techniques.
• Expertise in time series forecasting and handling temporal data.
• Experience with MLOps practices for production-scale deployments.
• Familiarity with cloud ML services (AWS SageMaker, Azure ML, Google Cloud AI Platform).
• Strong problem-solving and communication skills.
• Preferred / Nice to Have Solid SQL skills and experience with data extraction/transformation.
• Knowledge of modern data engineering tools (Airflow, Spark, dbt, Snowflake, or similar).
• Experience with CI/CD for ML workflows.

Caderno Nacional