Senior Data Scientist: Time Series & Scheduling Optimization

SoftServe; Town of Poland (NY); On-site; USD 140,000 - 190,000; Full time

Job summary

SoftServe is seeking a skilled ML Engineer to design and deploy classical ML solutions within the AI and Data Science Center of Excellence. You will transform complex tabular and time-series data into production-ready models that drive operational efficiency.

Join a team of 170+ experts and collaborate with stakeholders to deliver forecasting, optimization, and dynamic scheduling use cases, with opportunities to explore Generative AI intersections across the AI spectrum.

Qualifications

• Master's or PhD in relevant field required.
• Strong foundation in time series and statistical methods.
• Experience deploying ML models to cloud platforms.
• Ability to translate business needs into ML solutions.

Responsibilities

• Design time series forecasting models (ARIMA, Prophet) for demand planning.
• Build end-to-end ML pipelines for tabular data from ingestion to production deployment.
• Collaborate with stakeholders to translate challenges into scalable ML solutions.
• Develop optimization and dynamic scheduling using OR-Tools or PuLP.
• Apply statistical methods to uncover actionable insights.
• Establish monitoring and retraining for production models.
• Document methodologies and results for technical and non-technical audiences.

Skills

Forecasting

Statistical analysis

Python programming

Data pipelines

Model deployment

Communication

English (fluid)

Education

Master's or Ph.D. in CS/Math/Stats/OR

Tools

scikit-learn

XGBoost

LightGBM

statsmodels

Prophet

OR-Tools

PuLP

AWS/GCP/Azure

Job description

SoftServe is seeking a skilled ML Engineer to design and deploy classical ML solutions within the AI and Data Science Center of Excellence. You will transform complex tabular and time-series data into production-ready models that drive operational efficiency.

Join a team of 170+ experts and collaborate with stakeholders to deliver forecasting, optimization, and dynamic scheduling use cases, with opportunities to explore Generative AI intersections across the AI spectrum.