Remote ML Engineer: Geospatial AI for Forests

Vibrant Planet; Northern (KY); Hybrid; USD 100,000 - 200,000; Full time

Benefits offered by this job

Health, dental, and vision insurance

401(k) plan

Unlimited PTO policy

Company equity

Cell phone stipend (per pay period)

Home office setup allowance (one-time)

Job summary

Vibrant Planet is seeking an ML Engineer to build and operationalize foundation-model based deep learning systems for forest structure estimation from remote sensing data. You will adapt models, curate datasets, and integrate them into automated pipelines, collaborating with SciDev, Data Engineering, and Product to translate requirements.

The role emphasizes remote-first work, strong Python and geospatial skills, and experience with Airflow, Docker, and AWS.

Qualifications

• M.S. or higher in a quantitative field and equivalent experience.
• 3+ years of experience developing, training, and deploying deep learning models (PyTorch preferred).
• Strong Python proficiency with data science stack (NumPy, pandas, xarray, scikit-learn).
• 3+ years of experience with geospatial data processing (rasterio, GDAL, geopandas, shapely).
• Experience building and maintaining data pipelines with workflow orchestration tools (Airflow, Prefect, Dagster).
• Proficiency with Git, GitHub, and collaborative software development practices (code review, CI/CD).
• Experience with containerization (Docker) and cloud platforms (AWS preferred).
• Familiarity with STAC specifications and geospatial data catalog infrastructure.
• Strong written communication skills; ability to contribute to scientific manuscripts.
• Basic knowledge of forest ecology, remote sensing principles, or natural resource science.

Responsibilities

• Adapt and fine-tune geospatial foundation models for domain-specific heads.
• Prepare and manage training datasets from remote sensing sources and field inventories.
• Evaluate model performance with remote sensing metrics and validation data.
• Contribute to experiment design and hyperparameter optimization in collaboration with leads.
• Integrate trained models into automated geospatial data pipelines as containerized services.
• Build and maintain STAC infrastructure for data discovery and access control.
• Design larger orchestration pipelines (Airflow) and ensure observability and fault tolerance.
• Maintain data ingestion, preprocessing, and quality control for imagery and datasets.
• Monitor pipeline health and trigger automated retraining when needed.
• Develop model cards describing methods and performance.

Skills

Python

Geospatial data processing

Airflow

Docker

Git / GitHub

AWS

STAC

Remote sensing

Scientific communication

Education

M.S. in Computer Science, Machine Learning, Remote Sensing, Data Science, Ecology, or related field

Ph.D. in a relevant field

Tools

GitHub

Job description

Vibrant Planet is seeking an ML Engineer to build and operationalize foundation-model based deep learning systems for forest structure estimation from remote sensing data. You will adapt models, curate datasets, and integrate them into automated pipelines, collaborating with SciDev, Data Engineering, and Product to translate requirements.

The role emphasizes remote-first work, strong Python and geospatial skills, and experience with Airflow, Docker, and AWS.