We are tech transformation specialists, uniting human expertise with AI to create scalable tech solutions.
With over 8,000 CI&Ters around the world, we’ve built partnerships with more than 1,000 clients during our 30 years of history. Artificial Intelligence is our reality.
We are looking for a Data & Analytics Engineer supporting an AI/ML implementation for demand forecasting and resource optimization in the public transportation / fare collection industry. Works alongside an AWS ProServe ML Specialist on EDA, feature engineering, capacity modeling, and operational dashboards.
Responsibilities:
-
Exploratory Data Analysis (EDA):
- Conduct EDA and statistical profiling to identify trends and insights from data.
- Perform feature engineering specifically for time-series forecasting.
-
Data Wrangling and Preparation:
- Extract and transform data from relational databases (RDS, Oracle, PostgreSQL) into analytics-ready formats.
- Develop pipelines for data ingestion and processing.
-
Machine Learning Modeling:
- Build classical ML models for time-series forecasting, regression, and capacity/throughput modeling.
- Evaluate model performance using metrics such as RMSE, MAE, and MAPE, documenting performance results.
-
Data Visualization:
- Create insightful data visualizations and dashboards using Amazon QuickSight or equivalent BI tools.
-
Python Data Stack:
- Utilize the Python data stack (pandas, NumPy, scikit-learn, matplotlib/seaborn) for data manipulation and analysis.
-
Model Explainability:
- Apply SHAP or other model explainability techniques to interpret model outputs.
-
Collaboration and Communication:
- Work closely with stakeholders to translate business rules into effective feature engineering pipelines.
- Engage in milestone-driven, Firm Fixed Price delivery models, ensuring timely project completion.
Requirements for this challenge:
- 4+ years in data engineering or applied data science roles, preferably with experience on AWS.
- Proficient in exploratory data analysis (EDA), statistical profiling, and feature engineering for time-series forecasting.
- Experience in data wrangling from relational databases (RDS, Oracle, PostgreSQL) into analytics-ready formats.
- Strong understanding of classical ML modeling techniques, including time-series forecasting and regression.
- Familiarity with model evaluation metrics (RMSE, MAE, MAPE) and performance documentation.
- Experience in data visualization and dashboard development using Amazon QuickSight or equivalent BI tools.
- Hands-on experience with Amazon SageMaker (training, evaluation, Clarify).
- Proficient in the Python data stack, including pandas, NumPy, scikit-learn, matplotlib, and seaborn.
- Working knowledge of SQL and dimensional modeling.
- Familiarity with SHAP or model explainability techniques is a plus.
Expected Certifications
- AWS Certified Cloud Practitioner
- AWS Certified Data Engineer – Associate
- AWS Certified Machine Learning – Associate or AWS Certified Machine Learning – Specialty
#LI-LO1