APL is looking to advance the state-of-the-art in autonomous systems, uncrewed air systems, artificial intelligence, software design, embedded systems, virtual reality, and simulation to ensure the nation maintains an operational advantage on the future battlefield through foundational advances in artificial intelligence, autonomy, manned-unmanned teaming and novel unmanned aircraft design and testing.
Requirements
- Possess direct experience or significant academic project work in Reinforcement Learning.
- Are proficient in Python and have hands-on experience with at least one major deep learning framework (e.g., PyTorch, TensorFlow).
- Have a solid understanding of the mathematical foundations of ML, including probability, statistics, and linear algebra.
- Have experience with advanced RL topics such as multi-agent RL (MARL), inverse RL (IRL), or hierarchical RL (HRL).
- Possess a background in control theory (e.g., Model Predictive Control, optimal control), game theory, or dynamical systems
- Have demonstrated experience with robotics or aerospace simulation platforms (e.g., Gazebo, AirSim, AFSIM, MATLAB/Simulink).
- Have demonstrated experience applying advanced data analysis techniques or explainable AI to understand complex system behaviors.
Responsibilities
- Design, implement, and train reinforcement learning (RL) agents for complex, multi-agent collaborative and competitive tasks in the aerospace and defense domain.
- Develop novel solutions for uncrewed aerial systems (UAS) and drones, enabling sophisticated autonomous behaviors like coordinated flight, resource allocation, and adaptive tactics.
- Integrate and test intelligent agents within high-fidelity simulation environments, analyzing emergent behaviors, performance metrics, and system robustness under various conditions.
- Apply your knowledge of reinforcement learning, game theory, dynamical systems, and/or control theory to build agents that are not only intelligent but also stable and physically plausible.
- Collaborate with a cross-functional team of AI researchers, robotics engineers, and domain experts to translate mission objectives into solvable RL problems.
- Contribute to the full research and development lifecycle, from algorithm selection and experimentation to the analysis and presentation of results.
Other
- Hold a Bachelor’s degree in Aerospace Engineering, Electrical Engineering, Mechanical Engineering, Computer Science, Mathematics, Physics or a related technical field.
- Have at least 2+ years of professional, hands-on experience applying machine learning techniques to challenging problems.
- Are able to obtain an Interim Secret level security clearance by your start date and can ultimately obtain a TS/SCI level clearance.
- Hold a Master’s degree or PhD in Aerospace Engineering, Electrical Engineering, Mechanical Engineering, Computer Science, Mathematics, Physics or a related technical field.
- Have contributed to publications or presentations at relevant AI or robotics conferences.
