Computer Vision Scientist
Software Engineering
Remote
Computer Vision Scientist
Location: Remote (US)
Job Type: Contract
Interview Process: Virtual
About the Role
We are seeking a highly skilled Computer Vision Scientist to develop and deploy next-generation machine learning and computer vision solutions that transform large-scale agricultural and biological imaging data into actionable insights.
In this role, you will work at the intersection of computer vision, deep learning, geospatial analytics, and MLOps, building production-grade systems that leverage multimodal datasets including RGB imagery, multispectral data, LiDAR, and 3D point clouds.
You will collaborate with multidisciplinary teams of scientists, engineers, data analysts, and agronomy experts to deliver scalable AI solutions that drive innovation in plant phenotyping, precision agriculture, and digital farming technologies.
What You'll Do
Computer Vision & Deep Learning
- Design, train, evaluate, and deploy state-of-the-art computer vision models for:
- Object detection
- Image classification
- Semantic and instance segmentation
- Feature extraction
- 3D scene understanding
- Develop solutions using multimodal datasets including RGB imagery, multispectral imagery, LiDAR, and point clouds.
- Build scalable pipelines for automated image preprocessing, annotation, feature engineering, and model inference.
- Optimize model performance through calibration, validation, and continuous experimentation.
Machine Learning Engineering & MLOps
- Take machine learning solutions from research to production.
- Build robust training, deployment, monitoring, and retraining workflows.
- Implement CI/CD pipelines for machine learning applications.
- Develop APIs and services to support real-time and batch inference workloads.
- Collaborate with data engineers to build reliable and scalable data pipelines.
Software Engineering
- Write clean, maintainable, and testable Python code following software engineering best practices.
- Develop reusable frameworks and libraries for machine learning workflows.
- Implement unit, integration, and performance testing to ensure production reliability.
- Work within Linux environments and automate workflows through scripting.
Cloud & Infrastructure
- Deploy machine learning solutions using Docker, Kubernetes, and AWS services.
- Design scalable cloud-native architectures supporting high-volume image processing workloads.
- Monitor and optimize production systems for performance, reliability, and cost efficiency.
Cross-Functional Collaboration
- Partner with scientists, researchers, and business stakeholders to translate complex scientific problems into AI-driven solutions.
- Present technical findings and recommendations to both technical and non-technical audiences.
- Contribute to technical documentation, knowledge sharing, and best practices across teams.
Minimum Qualifications
- Master's or PhD in Computer Science, Machine Learning, Computer Vision, Artificial Intelligence, Statistics, Engineering, or a related field.
- 5+ years of industry experience developing computer vision and machine learning systems.
- Advanced proficiency in Python and software engineering best practices.
- Strong experience with machine learning and deep learning frameworks such as:
- PyTorch
- TensorFlow
- Scikit-learn
- Experience building object detection, segmentation, and classification models.
- Hands-on experience with OpenCV and image processing workflows.
- Strong understanding of Docker, Kubernetes, AWS, and cloud-native deployment patterns.
- Experience using SQL, Git, CI/CD pipelines, and MLOps tools.
- Excellent verbal and written communication skills.
- Professional English proficiency.
Preferred Qualifications
- Experience working with:
- LiDAR
- Multispectral imagery
- Hyperspectral imagery
- 3D point clouds
- Geospatial datasets
- Knowledge of GDAL, Rasterio, PostGIS, or related geospatial technologies.
- Experience with plant phenotyping, digital agriculture, biological imaging, or precision agriculture.
- Familiarity with data labeling platforms and computer vision annotation workflows.
- Experience working within Agile, Scrum, or Kanban teams.
- Portuguese language proficiency.
Nice-to-Have Technologies
Computer Vision
- OpenCV
- YOLO
- Detectron2
- MMDetection
- Segment Anything (SAM)
Deep Learning
- PyTorch
- TensorFlow
- Keras
- ONNX
Geospatial & Remote Sensing
- GDAL
- Rasterio
- ArcGIS
- QGIS
- PostGIS
Cloud & MLOps
- AWS
- Docker
- Kubernetes
- MLflow
- SageMaker
- Airflow
Programming
- Python
- SQL
- Bash
- Git
Medical, dental, and vision insurance are available to qualified candidates who meet eligibility requirements.