AI Software Engineer – Level 3

Northrop Grumman Northrop Grumman · Aerospace · Dulles, VA +1 · Software

AI Software Engineer focused on Reinforcement Learning (RL) and Supervised Learning (SL) for intelligent autonomy in space and aerospace programs. Responsibilities include R&D of novel algorithms, prototyping in Python/JAX/PyTorch, porting to C++/CUDA, developing physics-based autonomy for mission planning and decision-making, anomaly detection, and leading verification and flight readiness campaigns. Requires a TS/SCI clearance and experience with ML in a product line environment, translating literature to code, and physics-based AI applications.

What you'd actually do

  1. Perform Novel Algorithm R&D
  2. Design and implement state-of-the-art RL / SL algorithms drawn from the latest literature
  3. Rapidly prototype in Python/JAX/PyTorch, then port to embedded C++/CUDA
  4. Develop Physics-Based Autonomy to perform Mission Planning & Decision-Making
  5. Apply supervised learning, reinforcement learning, and other AI/ML techniques to high-fidelity astrodynamics planning and controls problems, including real-time constraint handling

Skills

Required

  • Bachelor's degree with a minimum of 5 years of relevant AI engineering experience or Master's degree with a minimum of 3 years or PhD with a minimum of 1 year
  • Industry knowledge and/or foundational education of AI, with a focus on ML, RL, or SL model development
  • Experience with machine learning usage in a product line environment
  • Experience with hands-on coding of learning algorithms from primary literature—comfortable translating equations to optimized code
  • Experience with physics-based AI application (e.g. for spacecraft, robotics, autonomous aircraft, drones, rockets, or similar) in academia or industry
  • Experience in developing scalable RL/SL and other ML pipelines, with a track record of designing novel algorithms
  • Ability to obtain and maintain a U.S. Government DoD Top-Secret (TS) security clearance and Sensitive Compartmented Information (SCI) approval/access

Nice to have

  • Python/JAX/PyTorch prototyping
  • Embedded C++/CUDA porting
  • Hierarchical or policy-gradient RL
  • Neural search or differentiable optimization
  • GNC filters
  • Digital twin campaigns

What the JD emphasized

  • Top Secret
  • TS/SCI
  • Physics-Based Autonomy
  • RL/SL algorithms
  • Novel Algorithm R&D
  • real-time anomaly detection
  • real-time constraint handling

Other signals

  • AI/ML
  • Reinforcement Learning
  • Autonomy
  • Spacecraft Operations
  • Algorithm R&D