Principal AI Engineer

Responsibilities

• Lead full-lifecycle computer vision and machine learning engineering from problem formulation and dataset curation through training, validation, deployment, and error analysis.
• Improve model robustness and domain adaptation across satellite sensors, geographic regions, resolutions, viewing conditions, weather, lighting, and seasonal variation.
• Ensure models are trained, versioned, deployed, monitored, and maintained reliably in production.
• Build and operate geospatial data and computer vision pipelines and AWS-based GPU training and inference workloads.
• Optimize production ML systems for inference latency, throughput, memory utilization, GPU efficiency, and cost.
• Communicate architecture decisions, experimental results, tradeoffs, risks, and recommendations to technical and non-technical stakeholders.
• Provide technical leadership and mentorship, lead design reviews and experiment planning, and contribute to proposals and white papers.

Requirements

• At least 12 years of hands-on software engineering experience, including at least four years developing computer vision or machine learning solutions for geospatial, remote-sensing, or similarly complex imagery.
• Bachelor’s degree in computer science, engineering, mathematics, or a related quantitative field, or equivalent practical experience.
• Expert-level Python proficiency and experience developing deep learning systems with PyTorch or comparable ML frameworks.
• Experience designing, training, evaluating, and deploying production computer vision models for detection, segmentation, change detection, classification, or time-series analysis.
• Strong experience with remote-sensing imagery and geospatial challenges involving spatial resolutions, viewing geometries, sensors, and environmental conditions.
• Hands-on experience with geospatial data and computer vision pipelines using Rasterio, GDAL, GeoPandas, Shapely, xarray, Zarr, or similar tools.
• Experience taking computer vision capabilities from experimentation through production, including evaluation, deployment, and performance optimization.
• Experience developing and operating AWS ML workloads, including GPU-based training and inference.
• Ability to provide technical leadership and mentorship without requiring direct management authority.
• U.S. citizenship is required for the supported work.
• Preferred qualifications include a master’s degree or Ph.D., 15 or more years of relevant experience, experience with multiple commercial and government remote-sensing sources, modern MLOps practices, foundation models, vision-language models, multimodal approaches, self-supervised learning, and significant domain-shift adaptation.
• Preferred experience includes rapidly developing prototypes or proof-of-concept applications and communicating results through demonstrations, proposals, white papers, or other technical materials.

Benefits

• Medical, dental, vision, disability, group term life, AD&D, voluntary life, and AD&D insurance.
• BlackSky pays 100% of employee-only medical, dental, and vision premiums and contributes $100 per month toward out-of-pocket expenses.
• 15 days of PTO, 11 company holidays, four floating holidays, one day of paid volunteerism leave annually, parental leave, and additional leave programs.
• 401(k) pre-tax and Roth options with employer match.
• Flexible Spending Accounts, Employee Stock Purchase Program, Employee Assistance and Travel Assistance Programs, and employer matching donations.
• Professional development, choice of Mac or PC, and company swag.
• Preferred location is near Herndon, Virginia, or Seattle, Washington, with strong remote candidates considered; the posting includes a Seattle salary range and is marked remote.