ETRM Data Scientist

Job Description:

Education Requirements:

o Masters degree in mathematics, Statistics, Data Science, or related fields is

mandatory.

o A Ph.D. in Mathematics, Statistics, Data Science, or similar areas is preferred but

not mandatory.

Mandatory skills:

o Data Science:

Extensive experience in time-series forecasting, predictive modelling, and

deep learning.

Proficient in designing reusable and scalable machine learning systems.

Proficiency in implementing techniques such as ARIMA, LSTM, Prophet,

Linear Regression, and Random Forest to ensure accurate forecasting

and insights.

Strong command of machine learning libraries, including scikit-learn,

XGBoost, Darts, TensorFlow, and PyTorch, along with data manipulation

tools like Pandas and NumPy.

Proven expertise in designing and implementing explicit ensemble

techniques such as stacking, boosting and bagging to improve model

accuracy and robustness.

Proven track record of analysing and optimizing performance of

operational machine learning models to ensure long-term efficiency andreliability.

Expertise in retraining and fine-tuning models based on evolving data

trends and business requirements.

o MLOps Implementation:

Proficiency in leveraging Python-based MLOps frameworks for

automating machine learning pipelines, including model deployment,

monitoring, and periodic retraining.

Advanced experience in using the Azure Machine Learning Python SDK

to design and implement parallel model training workflows, incorporating

distributed computing, parallel job execution, and efficient handling of

large-scale datasets in managed cloud environments.

o PySpark Proficiency

Strong experience in PySpark for scalable data processing and analytics.

o Azure Expertise:

Azure Machine Learning: Managing parallel model training, deployment,

and operationalization using the Python SDK.

Azure Databricks: Collaborating on data engineering and analytics tasks

using PySpark/Python.

Azure Data Lake: Implementing scalable storage and processing

solutions for large datasets.

Preferred skills:

o K-Means Clustering: Experience in applying k-means clustering for data

segmentation and pattern identification.

o Bottom-Up Forecasting: Skilled in creating granular bottom-up forecasting

models for hierarchical insights.

o Azure Data Factory : Designing, orchestrating, and managing pipelines for

seamless data integration and processing.

o knowledge of power trading concepts.

o Generative AI (GenAI): Experience in applying generative AI models, such as

GPT or similar frameworks.