AI/ML Engineer

Required skills: Python, PyTorch, Pandas, NumPy, AI, Machine Learning 🔍 AI/ML Engineer (Reinforcement Learning) Location: 100% remote Contract type: B2B Capacity: Full-time Rate: 130 - 160 PLN + VAT / h 🚀 About the project We are developing an intelligent Energy Management System (EMS) for commercial and industrial facilities. The system uses data on energy consumption, renewable energy production, electricity prices, and battery status to determine when energy should be consumed, stored, purchased from the grid, or sold back. The core of the project is the development of Reinforcement Learning models combined with mathematical optimization and energy system simulation . You will work on RL-based control strategies, define their decision environments and constraints, build optimization models as benchmarks, and develop simulations of batteries, PV installations, and energy flows. The goal is to reduce energy costs and maximize the use of renewable energy while respecting the technical constraints of each installation. 💡 Who we are Kyotu Technology is a boutique software house based in Wrocław and Warsaw, working fully remotely or in hybrid mode across Poland. We focus on long-term, high-quality engineering and building complex, production-grade systems with real business impact. Our teams have real influence on technical and architectural decisions. 🧠 Your responsibilities training, testing, and improving Reinforcement Learning models developing mathematical optimization models and using them as benchmarks for RL-based solutions defining objective/reward functions, constraints, states, actions, and decision spaces developing and improving simulations of batteries, PV installations, and energy flows evaluating RL models against optimization-based solutions and baseline control strategies analyzing model behavior and experimental results to identify areas for improvement validating solutions across different installation configurations and energy consumption profiles researching and evaluating different approaches to energy optimization problems preparing and processing data related to energy consumption, PV production, weather, and electricity prices occasionally supporting electricity price forecasting models for the day-ahead market 🧩 Must haves hands-on experience with Reinforcement Learning , including practical experience with at least one algorithm such as DQN or PPO practical experience deploying Machine Learning models into production environments ability to define reward functions, states, actions, constraints, and decision spaces for RL environments solid understanding of mathematical optimization fundamentals very good knowledge of Python strong experience with PyTorch or another deep learning framework such as TensorFlow very good knowledge of pandas and NumPy practical experience training, testing, evaluating, and comparing Machine Learning models ability to work with optimization problems combining discrete and continuous decisions strong understanding of experimentation, benchmarking, and interpretation of model results ability to write clean, maintainable, and testable Python code experience with Git high level of independence and ownership, including the ability to define and prioritize the next steps of the project English at B2 level or higher ✨ Nice to have knowledge of energy systems, renewable energy, battery storage, or energy markets experience with Gymnasium or TorchRL experience with linear programming, MILP, or dynamic programming experience with time-series forecasting practical experience preparing and analyzing time-series datasets knowledge of neural network architectures for forecasting, such as TFT or TiDE experience with Optuna, DVC, or MLflow experience working with weather, renewable energy production, energy consumption, or electricity price data experience using AI coding assistants such as Claude Code or Codex experience with Docker and/or Kubernetes 📦 What we offer B2B contract rate: 130 - 160 PLN + VAT / h 100% remote work long-term cooperation technically challenging project combining ML, Reinforcement Learning, optimization, and energy systems high level of independence and ownership real influence on technical decisions and the direction of the solution opportunity to work on models that directly impact energy costs and renewable energy utilization collaboration with experienced engineering and AI/ML specialists