Senior Machine Learning Engineer

Skills

About the Role

You will design, train, and productionize machine learning models for aerial imagery, including classification, object detection, and 2D/3D segmentation. You will integrate foundation models, build change-detection and predictive time-series models, develop generative multimodal and vision-language systems, and operate scalable ML pipelines on AWS to move prototypes into production.

Requirements

• M.S. in a quantitative field and 5+ years of relevant work experience
• Proven ability to translate research into production including rapid prototyping and distillation of research findings
• At least 3 years of applied ML and computer vision experience transitioning models from research to production
• Experience with geospatial aerial or satellite imagery and large imagery datasets in cloud environments
• Working knowledge of SAM2 or similar algorithms including fine-tuning prompt design and distillation
• Hands-on experience building generative AI systems including multimodal RAG vision-language models and diffusion pipelines
• Production experience operating ML pipelines on AWS particularly SageMaker and related data orchestration services
• Experience optimizing models for real-world performance throughput and cost efficiency
• Preferred Ph.D. and 7+ years blending AI with physical sciences or photogrammetry
• Preferred expertise with geospatial workflows projections coordinate reference systems and tools like GDAL PostGIS and rasterio
• Preferred experience with 3D scene understanding using NeRFs Gaussian Splatting and point cloud segmentation
• Preferred experience architecting multimodal RAG systems integrating imagery vector and time-series data

Responsibilities

• Design train and productionize models for aerial-image classification object detection and 2D/3D segmentation
• Integrate and optimize foundation models for aerial segmentation including SAM2-like capabilities through prompt engineering fine-tuning and distillation
• Engineer change detection and structure-change models that distinguish physical changes from acquisition noise and lighting variation
• Develop predictive models that combine time-series methods with spatial context for trend forecasting
• Build generative AI capabilities including multimodal models and natural-language query systems grounded in georeferenced pixels
• Design and operate scalable ML pipelines on AWS using SageMaker S3 and Step Functions
• Track and translate research advances such as NeRFs Gaussian Splatting and diffusion models into product capabilities
• Establish evaluation benchmarks and metrics to validate model performance under production conditions

Benefits

• Remote-friendly environment with a hub in Vancouver Canada
• Flexible hours
• Medical dental and vision health benefits