SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 100,000 - 200,000 / annual
Vibrant Planet is seeking a Machine Learning Engineer to develop, train, and deploy deep learning models for geospatial analysis and forest monitoring. You will work on a remote-first team spanning science, engineering, and product to build ML systems that process satellite imagery and geospatial data at scale.
Key responsibilities include:
- Developing and training deep learning models (PyTorch) for remote sensing applications
- Building and maintaining robust data pipelines with workflow orchestration tools (Airflow, Prefect, Dagster, or equivalent)
- Processing large-scale geospatial datasets using tools like rasterio, GDAL, and geopandas
- Deploying models to production using containerization (Docker) and cloud platforms (AWS preferred)
- Collaborating with scientists and engineers to translate domain knowledge into ML solutions
- Contributing to scientific manuscripts and technical documentation
- Following secure development practices and maintaining data integrity
- Working independently in a remote environment with strong self-motivation and time management
You will engage with geospatial data standards (STAC specifications), experiment tracking tools, and potentially distributed computing systems. The role emphasizes both technical depth and cross-functional communication.
REQUIRED QUALIFICATIONS:
- M.S. in Computer Science, Machine Learning, Remote Sensing, Data Science, Ecology, or related quantitative field (or equivalent work experience)
- 3+ years developing, training, and deploying deep learning models (PyTorch preferred)
- Strong Python proficiency with data science stack (NumPy, pandas, xarray, scikit-learn)
- 3+ years experience with geospatial data processing (rasterio, GDAL, geopandas, shapely)
- Experience building and maintaining data pipelines with workflow orchestration tools
- Proficiency with Git, GitHub, and collaborative software development (code review, CI/CD)
- Experience with containerization (Docker) and familiarity with cloud platforms (AWS preferred)
- Familiarity with STAC specifications and geospatial data catalog infrastructure
- Strong written communication skills; ability to contribute to scientific manuscripts and technical documentation
- Basic knowledge of forest ecology, remote sensing principles, or natural resource science
PREFERRED QUALIFICATIONS:
- 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 (MLflow, W&B) and model registry practices
- Experience with database systems (PostgreSQL, PostGIS) and message queues
- Publications in remote sensing, ML, or ecology journals
