Staff Engineer, World Model Development - Remote

OpenKrill; United States; Hybrid; USD 180,000 - 250,000; Full time

Benefits offered by this job

Health insurance

Dental insurance

Life insurance

Flexible PTO

401k with match

Job summary

Merlin Labs is seeking a senior AI/ML engineer to design, train and evaluate world models predicting aircraft state and environment, and to build rollout and imagination machinery for planner evaluation. You will own predictive uncertainty signals and validate across flight regimes, weather and traffic conditions.

Collaborating with Data/Sim teams, you will compare learned dynamics to physics-based models, ensure reproducibility, and drive deployment toward real-world autonomy across aircraft

Qualifications

• Degree in Computer Science, AI, Data Science, Computer Engineering, Applied Math, or related field.
• 10+ years building and training deep learning models, with sequence, dynamics, video or trajectory prediction.
• Strong PyTorch and a solid grasp of the training stack—distributed training, mixed precision, experiment tracking, debugging a run that has silently gone wrong.
• Working knowledge of dynamical systems, state estimation or control; read a flight dynamics model and know what your network is and is not replacing.
• Demonstrated rigor in evaluation and uncertainty quantification.
• Comfort with messy real-world sensor and telemetry data.

Responsibilities

• Design, train and evaluate world models that predict evolution of aircraft state, environment and other traffic under candidate action sequences.
• Build the rollout and imagination machinery that lets a planner evaluate candidate plans against predicted outcomes.
• Own uncertainty: calibrated predictive uncertainty and out-of-distribution signals required by safety monitoring.
• Characterize model validity boundaries across flight regimes, weather, traffic densities and configurations.
• Work the sim-to-real gap with Data/Sim team: train in simulation, validate against flight data, feed discrepancies back into simulator fidelity.
• Benchmark learned dynamics against Merlin's physics-based models and flight-controls models.
• Contribute to shared eval harness and ensure reproducibility: every result traceable to data version, config and seed.

Skills

Deep learning

PyTorch

Uncertainty quantification

Evaluation rigor

Sensor/telemetry data

Experiment tracking

Education

Bachelor’s or higher in CS/AI/Data Science/Eng

Tools

Distributed training

Mixed precision

Debugging runs

Flight data use

Job description

Merlin Labs is seeking a senior AI/ML engineer to design, train and evaluate world models predicting aircraft state and environment, and to build rollout and imagination machinery for planner evaluation. You will own predictive uncertainty signals and validate across flight regimes, weather and traffic conditions.

Collaborating with Data/Sim teams, you will compare learned dynamics to physics-based models, ensure reproducibility, and drive deployment toward real-world autonomy across aircraft