Staff Engineer, World Model Development

Sourced from emploive.com

Merlin Labs is seeking a Staff Engineer to design and train world models for autonomous aircraft systems. This role focuses on predicting aircraft state and environment evolution to enable safe, full-stack autonomy from takeoff to touchdown. The ideal candidate will bridge the gap between simulation and real-world flight data while ensuring rigorous uncertainty quantification.

• Design, train, and evaluate world models for aircraft state and traffic prediction.
• Build rollout and imagination machinery for planner evaluation of candidate plans.
• Own calibrated predictive uncertainty and out-of-distribution signals for safety monitoring.
• Characterize model validity boundaries across different flight regimes and weather conditions.
• Work the sim-to-real gap by validating trained models against flight data.

• 10+ years building and training deep learning models, specifically in sequence or trajectory prediction.
• Strong proficiency in PyTorch and distributed training stacks.
• Working knowledge of dynamical systems, state estimation, or control theory.
• Demonstrated rigor in evaluation metrics and uncertainty quantification.