Introduction
We are seeking a Reinforcement Learning Engineer who specializes in developing agents capable of learning through interaction and feedback. If you are passionate about building intelligent systems for robotics, gaming, finance, or operations research, this role provides the opportunity to advance state-of-the-art decision-making AI.
As a Reinforcement Learning Engineer at our organization, you will design RL algorithms, run large-scale experiments, and collaborate with cross-functional teams to apply reinforcement learning in practical, high-impact domains.
We offer competitive compensation, comprehensive benefits, and opportunities to contribute to cutting-edge research and real-world applications of reinforcement learning.
Objectives of this role
- Develop reinforcement learning algorithms for real-world environments.
- Design scalable training pipelines for RL agents.
- Collaborate with researchers and engineers to apply RL to industry use cases.
- Benchmark and evaluate RL models for performance and stability.
Your tasks
- Implement RL algorithms (Q-learning, policy gradients, actor-critic methods).
- Run experiments in simulated and real-world environments.
- Integrate RL solutions into robotics, simulation, or operational systems.
- Optimize reward functions and training processes for stability.
- Publish findings and contribute to open-source RL frameworks.
- Collaborate with research teams on advancing RL state of the art.
Required skills and qualifications
- Bachelor’s degree in Computer Science, Machine Learning, or related field.
- Strong programming skills in Python and ML frameworks (TensorFlow, PyTorch).
- Experience implementing and evaluating RL algorithms.
- Familiarity with simulation environments (OpenAI Gym, MuJoCo, Unity).
- Understanding of optimization techniques and probability theory.
Preferred skills and qualifications
- Advanced degree in AI, Robotics, or Applied Mathematics.
- Experience deploying RL in robotics, finance, or industrial applications.
- Familiarity with distributed training for reinforcement learning.
- Contributions to open-source RL libraries or research publications.
- Strong understanding of multi-agent reinforcement learning and safe RL.
