ML Researcher, World Models

Geolava; United States; Remote; USD 170,000 - 230,000; Full time

Benefits offered by this job

Competitive salary

Medical, dental, vision insurance

Retirement plan

Disability & life insurance

Job summary

Geolava is building spatial intelligence systems and seeking a PhD-level researcher to advance world-models with multi-temporal imagery and signals. You will train, evaluate, and refine predictive models, and work with AI and engineering teams to deploy capabilities onto Geolava's platform.

The role emphasizes rigorous experimentation, publication-ready documentation, and staying at the cutting edge of self-supervised and generative modeling for remote sensing data.

Qualifications

• World-model research experience with learned dynamics or related work in academia or industry.
• PhD in machine learning, computer vision, or related quantitative field.
• Fluent in deep learning for large vision models and foundation models.
• Strong experimental design with proper baselines and splits.
• Ability to operate in ambiguous, small-team settings and drive work to completion.
• Clear written and spoken technical communication for research and non-research audiences.

Responsibilities

• Design, train, and evaluate world models predicting asset changes over time and under interventions.
• Develop representation learning and predictive modeling on multi-temporal aerial/satellite data and signals.
• Build rigorous evaluation with baselines, temporal splits, calibration, and leakage-proof tests.
• Run experiments on cloud GPUs with emphasis on throughput and cost, turning results into decision-ready writeups.
• Collaborate with AI and engineering teams to deploy research into Geolava's platform.
• Keep current with world-models, self-supervised learning, and generative modeling literature.

Skills

World-model research

Deep learning

PyTorch

Vision transformers

Diffusion models

Python

Experiment design

Scientific communication

Education

PhD in machine learning, CV, or related field

Tools

PyTorch

OpenCV

GIS tooling

Cloud GPUs

Job description

At Geolava, we bring AI to the physical world. We are building spatial intelligence systems by leveraging world models to simulate the evolution of the physical world over time. We continuously model real-world dynamics, simulate actions, and forecast their impact on assets.

We are backed by top-tier VCs and have been revenue-generating from day one. This is your opportunity to join as a founding team member to help define the future of spatial intelligence from the ground up.

Responsibilities (What You'll Do)

• Design, train, and evaluate world models of the built environment that predict how assets change over time and in response to interventions and external forces.
• Develop representation learning and predictive modeling approaches over multi-temporal aerial and satellite imagery, property records, and other physical and administrative signals.
• Build rigorous evaluation for a domain with no public benchmarks: baselines, held-out temporal splits, calibration, and tests that distinguish genuine forecasting skill from leakage.
• Run experiments on cloud GPUs with attention to throughput and cost, and turn results into clear, decision-ready writeups.
• Work with the AI and engineering teams to take successful research into production as capabilities in Geolava's platform.
• Stay current with the world-model, self-supervised learning, and generative modeling literature, and bring the ideas that matter into our work.

Your Background

• World-model research experience. You have built or contributed to world models: learned dynamics models, latent predictive models, action-conditioned generation, or closely related work, in academia or industry. This is required.
• PhD. You hold a PhD in machine learning, computer vision, or a closely related field.
• Deep learning fluency. You are comfortable training large vision models, adapting foundation models efficiently, and diagnosing why a training run behaves the way it does.
• Empirical rigor. You design experiments to answer questions, insist on proper baselines and splits, and are honest about what the evidence does and does not show.
• Ownership. You are productive with ambiguous problems and small teams, and you drive work from idea through result without waiting for a roadmap.
• Clear communication. You write and speak precisely about technical work for both research and non-research audiences.

Technical Requirements

• PhD in machine learning, computer vision, or a related quantitative field.
• Demonstrated research work on world models or learned dynamics models, with publications, open-source work, or shipped systems to show for it.
• Expert-level PyTorch and experience training and fine-tuning vision transformers or diffusion models at scale.
• Strong Python and data engineering skills for large image and tabular datasets.
• Experience running training workloads on cloud GPU infrastructure.
• Experience with remote sensing, geospatial data, or spatiotemporal modeling is a strong plus.

Why Join Geolava?

• Be at the cutting edge of Physical AI.
• Competitive salary. Compensation varies according to candidate level and experience.
• Excellent benefits including medical, dental, and vision insurance, a retirement plan, short & long term disability and life insurance.

Geolava is committed to maintaining a drug-free workplace and promoting a safe, healthy working environment for all employees.

Geolava is an equal opportunity employer and has a global remote workforce. Applicants are considered solely based on their qualifications, without regard to an applicant's disability or need for accommodation. Any Geolava applicant who requires reasonable accommodations during the application process should contact Geolava's Human Resources Department to make the need for an accommodation known.