Senior Data Scientist, Reinforcement Learning

New
K
Kyotu TechnologyEnergy management
100% remote workContractSenior
Salary140 - 180 PLN per hour
Apply NowOpens the employer's application page

Job Details

Languages
English at B2 level or higher
Required Skills
PythonGitNumpyPyTorchPandasTensorflow

Requirements

  • Have commercial, hands-on experience developing, training, and evaluating reinforcement learning models.
  • Have practical experience with RL algorithms such as PPO, DQN, or similar approaches.
  • Be able to independently design RL environments, including reward functions, state representations, action spaces, and constraints.
  • Have experience evaluating RL agent performance, debugging training processes, and improving policies.
  • Understand mathematical optimization, including objective functions, constraints, and optimization-based decision-making.
  • Be able to formulate optimization problems involving discrete and continuous variables.
  • Have strong Python programming skills and practical experience with PyTorch, TensorFlow, or similar ML frameworks.
  • Have very good knowledge of pandas and NumPy.
  • Have experience training, evaluating, and comparing machine learning models and deploying them into production.
  • Have experience writing clean, maintainable, and testable Python code and using Git.
  • Have English proficiency at B2 level or higher.

Responsibilities

  • Design, train, evaluate, and improve reinforcement learning models for energy management and optimization.
  • Develop mathematical optimization models to benchmark and validate RL-based solutions.
  • Define RL environments, including reward functions, state and action spaces, and operational constraints.
  • Build and improve simulations of battery storage systems, photovoltaic installations, and energy flows.
  • Experiment with RL algorithms and optimization approaches to identify effective control strategies.
  • Analyze agent behavior, troubleshoot training issues, and improve model performance.
  • Compare RL policies against mathematical optimization models and baseline strategies.
  • Test solutions across different consumption patterns, installation configurations, and market conditions.
  • Process and analyze energy consumption, renewable production, weather, and electricity pricing data.
  • Occasionally contribute to electricity price forecasting models.
View Full Description & ApplyYou'll be redirected to the employer's site
140 - 180 PLN per hour
Apply Now