ML Engineer

Vibrant Planet•Truckee, CA

1d•Remote

About The Position

Vibrant Planet is seeking an ML Engineer to build, adapt, and operationalize foundation model-based deep learning systems that estimate forest structure metrics from remotely sensed data. The role is part of a team working at the intersection of machine learning, remote sensing, and forest ecology, developing models, pipelines, and data products for the Land Tender decision-support platform. The ML Engineer will fine-tune and adapt geospatial foundation models as backbones for custom neural network heads, integrate trained models into an automated production pipeline, and maintain supporting data infrastructure. The role also contributes to scientific publications and connects SciDev, Data Engineering, and Product teams. It is a full-time, remote U.S. position, with Pacific or Mountain time zones preferred, reporting to the Engineering Manager and Infra Lead.

Requirements

M.S. in Computer Science, Machine Learning, Remote Sensing, Data Science, Ecology, or a related quantitative field, or equivalent work experience.
At least 3 years of experience developing, training, and deploying deep learning models; PyTorch is preferred.
Strong Python proficiency, including NumPy, pandas, xarray, and scikit-learn.
At least 3 years of experience with geospatial data processing, including rasterio, GDAL, geopandas, and shapely.
Experience building and maintaining data pipelines with workflow orchestration tools such as Airflow, Prefect, Dagster, or equivalent.
Proficiency with Git and GitHub and collaborative software development practices, including code review and CI/CD.
Experience with containerization using Docker and familiarity with cloud platforms; AWS is preferred.
Familiarity with STAC specifications and geospatial data catalog infrastructure.
Strong written communication skills and ability to contribute to scientific manuscripts and technical documentation.
Basic knowledge of forest ecology, remote sensing principles, or natural resource science.
Ability to collaborate in interdisciplinary teams, maintain strong organization and clear workflow documentation, work independently in a remote-first environment, and communicate adaptively across scientific and engineering audiences.
Commitment to an inclusive and equitable work environment.

Nice To Haves

Ph.D. in a relevant field.
Experience with geospatial foundation models and self-supervised learning.
Experience with Kubernetes and distributed computing for large-scale inference.
Familiarity with ML experiment tracking tools such as MLflow or W&B and model registry practices.
Experience with database systems such as PostgreSQL and PostGIS, and message queues.
Publications in remote sensing, ML, or ecology journals.

Responsibilities

Adapt and fine-tune custom or publicly available geospatial foundation models as backbones for domain-specific deep neural network heads that estimate forest structure metrics such as canopy height, biomass, and basal area.
Prepare, curate, and manage training datasets from remote sensing sources, including Sentinel-2, Sentinel-1, Landsat, lidar, NAIP, and field plot inventories.
Evaluate model performance using standard remote sensing accuracy metrics and field-based validation data.
Contribute to experiment design, hyperparameter optimization, and ablation studies in coordination with the Technical Lead ML Engineer.
Integrate trained ML models into Vibrant Planet’s automated geospatial data pipeline as containerized, orchestrated inference services.
Build and maintain STAC infrastructure for discovery, cataloging, and access control of ML model inputs and outputs.
Design and implement larger pipelines composed of smaller Airflow DAGs, ensuring idempotency, observability, and fault tolerance.
Maintain and improve data ingestion, preprocessing, and quality-control workflows for satellite imagery and ancillary datasets.
Monitor pipeline health and model drift, and implement alerting and automated retraining triggers as needed.
Develop model cards summarizing modeling methods and performance.
Write and contribute to scientific manuscripts describing methods, validation results, and novel applications.
Serve as a cross-team link between SciDev, Data Engineering, and Product by translating requirements, communicating constraints, and aligning priorities.
Document pipelines, model architectures, and operational procedures in team knowledge bases.
Participate in code reviews, architectural discussions, and sprint planning.
Work collaboratively across science, engineering, and product teams; manage time and work independently in a remote-first environment; communicate across scientific and engineering audiences; and support an inclusive and equitable work environment.
Comply with the company’s information security policies and security responsibilities, including completing required training, safeguarding data and credentials, reporting suspected incidents or policy violations, following secure development and change-management practices, and addressing security vulnerabilities.