Statherós is a small DEFTECH firm focused on developing cutting-edge AI and autonomy systems for the US Department of Defense. They are seeking a talented AI Engineer specializing in Proximal Policy Optimization (PPO) to lead the development of AI-enabled algorithms that automate the operation of air traffic radar systems.
Responsibilities:
- Design, implement, and optimize Proximal Policy Optimization (PPO) algorithms for domain-specific use cases
- Develop and train reinforcement learning models for real-world applications, focusing on efficiency and scalability
- Collaborate with cross-functional teams to integrate PPO models into production systems
- Analyze model performance and experiment with hyperparameter tuning to achieve optimal results
- Stay up-to-date with the latest research and advancements in reinforcement learning and apply them to enhance existing solutions
- Build robust pipelines for training, evaluation, and deployment of RL models
- Document workflows, methodologies, and code for reproducibility and knowledge sharing