Staff Engineer, World Model Development

Merlin; Boston (MA); On-site; USD 150,000 - 230,000; Full time

Benefits offered by this job

Catered lunches

Snacks and beverages

On-site perks

Job summary

Merlin HQ in Boston seeks a senior ML engineer/scientist to design and train world models for aircraft dynamics and environment. You will build rollout mechanisms for planners to evaluate candidate plans against predicted outcomes and contribute to safety through calibrated uncertainty signals.

You will work with data/sim teams to bridge sim-to-real gaps, benchmark against physics-based models, and ensure reproducible results across data versions and seeds.

Qualifications

• 10+ years building and training deep learning models, including sequence or trajectory prediction.
• Experience with evaluation and uncertainty quantification in predictive models.
• Strong PyTorch and training stack knowledge: distributed training, mixed precision, experiment tracking.

Responsibilities

• Design, train and evaluate world models predicting aircraft state and environment.
• Build rollout/imagery machinery for planner evaluation of candidate futures.
• Own calibrated predictive uncertainty and out-of-distribution signals for safety monitoring.

Skills

Deep learning

Sequence modelling

PyTorch

Uncertainty quantification

Education

Degree in CS/AI/Data Science

Tools

Python

Distributed training

Job description

About Merlin:

Merlin (NASDAQ: MRLN) is a publicly traded aerospace and defense company building a non-human pilot to deliver full-stack autonomy for any aircraft from takeoff to touchdown. The Merlin Pilot autonomy system powers a growing range of aircraft and mission profiles and has been proven through hundreds of autonomous flights from Merlin's global flight test facilities, including Kerikeri, New Zealand; Quonset Point, Rhode Island; and soon, Bedford, Massachusetts. Headquartered in Boston, Merlin is expanding its organization to accelerate the development and deployment of its autonomy platform, helping customers solve some of aviation's most pressing challenges, from pilot shortages to improving flight safety. Backed by some of the world's leading investors prior to its public listing, Merlin continues to advance the certification and commercialization of autonomous flight across commercial and defense aviation.

About You:

You want to build a model that understands what happens next. Not a classifier, not a chatbot — a learned model of an aircraft moving through an environment, good enough that a planner can imagine several futures and pick one. You are as interested in where your model is wrong as in where it is right, because in this application the second question is the one that matters.

You'll own the learned predictive models of the aircraft, its environment and other actors in it — and the rollout machinery that turns those models into evaluated candidate futures.

Responsibilities:

• Design, train and evaluate world models that predict the 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 before committing to one


• Own uncertainty: calibrated predictive uncertainty and out-of-distribution signals are required outputs of your models, consumed directly by the safety monitoring layer


• Characterize model validity boundaries rigorously — the flight regimes, weather, traffic densities and configurations where predictions can be trusted, and where they degrade


• Work the sim-to-real gap in both directions with the Data/Sim team: train in simulation, validate against flight data, and feed discrepancies back into simulator fidelity


• Benchmark learned dynamics against Merlin's existing physics-based models and flight-controls models; be honest about where the classical approach wins


• Contribute to the shared eval harness and hold the line on reproducibility: every result traceable to a data version, a config and a seed

Qualifications:

• 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 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; you can 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

Nice to Have:

• Model-based RL, latent dynamics models or learned simulators


• Experience with trajectory prediction in autonomous driving or robotics


• Aerospace background: flight dynamics, aircraft performance or air traffic


• Multimodal fusion across vision, state and structured mission context

This position is based on-site at Merlin HQ in Boston, MA.

Once you’re here, you’ll enjoy a variety of on-site perks designed to make your workday enjoyable and convenient. These include catered lunches featuring a rotating menu of delicious options, an assortment of snacks to keep you fueled throughout the day, and a selection of beverages, including coffee, tea, and other drinks, to keep you refreshed.

Our goal is to create an environment where you can thrive both professionally and personally

Merlin Labs offers an innovative, entrepreneurial, and team-focused startup environment. We also offer a top-notch benefits package (health, dental, life, unlimited vacation, and 401k with match) and work/life integration. Being part of the Merlin team allows you to become part of a small team that supports professional development while working together to achieve our mission.

Merlin Labs is an equal opportunity employer and values diversity. We do not discriminate on the basis of race, religion, color, national origin, genetic information, sex (including pregnancy), gender, gender identity and expression, sexual orientation, age, marital status, military service or obligation or disability status, or any other characteristic protected by law. All job offers are contingent upon the candidate passing background and reference checks.

At this time, we are unable to provide visa sponsorship or consider candidates who require visa transfers. Applicants must be authorized to work in the United States without the need for visa sponsorship now or in the future.

In compliance with federal law, all persons hired will be required to verify identity and eligibility to work in the United States and to complete the required employment eligibility verification form upon hire.

If you require reasonable accommodation in completing an application, interviewing, completing any pre-employment testing, or otherwise participating in the employee selection process, please direct your inquiries to: [e-mail]

Merlin Labs does not accept unsolicited resumes from any source other than directly from candidates.

The compensation range provided is reflective of base salary only, and is a good-faith estimate based on a wide range of factors. The actual offer will be determined by a variety of factors including the candidate's qualifications, skills, experience, education, and training. Highly competitive equity grants are considered part of Merlin's total compensation package. Additionally, Merlin offers top-tier benefits for full-time employees.