Website Devi Technologies
🔧 What You’ll Be Working On:
✔️ Designing and developing RL algorithms for real-world applications (e.g. robotics, recommendation systems, finance)
✔️ Building simulation environments for training intelligent agents
✔️ Optimizing policy learning using techniques such as Q-learning, PPO, A3C, and DDPG
✔️ Collaborating with data scientists, engineers, and researchers to deploy RL models into production
✔️ Experimenting with model architectures (e.g., actor-critic, deep Q-networks, model-based RL)
✔️ Publishing findings and contributing to cutting-edge AI research and development
🎯 What We’re Looking For:
✔️ Strong expertise in reinforcement learning and deep learning frameworks (e.g. PyTorch, TensorFlow)
✔️ Solid understanding of MDPs, reward shaping, exploration-exploitation tradeoffs, and sample efficiency
✔️ Experience with simulation platforms (e.g., OpenAI Gym, MuJoCo, Unity ML-Agents)
✔️ Background in applied mathematics, statistics, and control theory is a plus
✔️ Strong coding skills in Python and familiarity with version control (Git)
✔️ Advanced degree (Master’s or PhD) in Machine Learning, Computer Science, Robotics, or related field
To apply for this job email your details to jobs@devitechs.co.uk
