Staff Engineer, World Model Development

Merlin Labs

. Design, train, and evaluate world models predicting aircraft state, environment, and other traffic under candidate action sequences .

Posted 9/17/2026full-timeBoston • Massachusetts • United StatesLead💰 $185,000 - $325,000 per yearWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Expertise in designing and training deep learning models for aircraft state and environment prediction, with a strong focus on uncertainty quantification and model evaluation. Proficient in utilizing simulation data to bridge the sim-to-real gap and improve model fidelity.

Highest-signal resume keywords

Deep Learning Model DevelopmentPyTorch ProficiencyDistributed TrainingUncertainty QuantificationDynamical Systems Knowledge

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Deep LearningSequence PredictionDynamics PredictionTrajectory PredictionExperiment TrackingDebugging Machine LearningMixed Precision TrainingState EstimationControl SystemsModel Evaluation

Soft Skills

Rigor in EvaluationProblem-Solving

Tools & Technologies

Simulation ToolsTelemetry Data AnalysisData Versioning

Industry Keywords

Artificial IntelligenceComputer ScienceData ScienceFlight DynamicsSafety Monitoring

Tech Stack

Tools & technologies

PyTorch

About the role

Key responsibilities & impact

Design, train, and evaluate world models predicting aircraft state, environment, and other traffic under candidate action sequences
Build rollout and imagination machinery for planners to evaluate candidate plans against predicted outcomes
Develop calibrated predictive uncertainty and out-of-distribution signals consumed by the safety monitoring layer
Characterize model validity boundaries across flight regimes, weather, traffic densities, and configurations
Work with the Data/Sim team on the sim-to-real gap by training in simulation, validating against flight data, and improving simulator fidelity
Benchmark learned dynamics against physics-based and flight-controls models
Contribute to the shared evaluation harness
Maintain reproducibility by tracing results to data versions, configurations, and seeds

Requirements

What you’ll need

Degree in Computer Science, Artificial Intelligence, Data Science, Computer Engineering, Applied Math, or a related subject
10+ years building and training deep learning models, with meaningful work on sequence, dynamics, video, or trajectory prediction
Strong PyTorch skills
Distributed training
Mixed precision
Experiment tracking
Debugging machine learning training runs
Working knowledge of dynamical systems, state estimation, or control
Ability to read a flight dynamics model and understand what a neural network is and is not replacing
Demonstrated rigor in evaluation and uncertainty quantification
Comfort with messy real-world sensor and telemetry data
Must be authorized to work in the United States without visa sponsorship now or in the future
Must pass background and reference checks

Benefits

Comp & perks

Catered lunches with a rotating menu
Snacks
Coffee, tea, and other beverages
Health insurance
Dental insurance
Life insurance
Unlimited vacation
401(k) with match
Work/life integration
Professional development support
Competitive equity grants
Top-tier benefits for full-time employees