Applied AI Scientist

Vantor is forging the new frontier of spatial intelligence, helping decision makers and operators navigate what’s happening now and shape what’s coming next. Vantor is a place for problem solvers, changemakers, and go-getters—where people are working together to help our customers see the world differently, and in doing so, be seen differently. Come be part of a mission, not just a job, where you can:
Shape your own future, build the next big thing, and change the world.

To be eligible for this position, you must be a U.S. Person, defined as a U.S. citizen, permanent resident, Asylee, or Refugee.

Export Control/ITAR:
Certain roles may be subject to U.S. export control laws, requiring U.S. person status as defined by 8 U.S.C. 1324b(a)(3).

• Design, develop, and deploy AI-driven applications that transform large-scale geospatial data into actionable insights and predictive intelligence.
• Build and operate end-to-end AI/ML pipelines including data ingestion, preprocessing, feature engineering, training, evaluation, and production inference.
• Productionize reasoning models, vision-language models (VLMs), and multimodal AI systems that combine imagery, geospatial signals, and structured data.
• Architect enterprise-grade training and experimentation frameworks, including automated pipelines, experiment tracking, benchmarking, and reproducible evaluation.
• Create synthetic datasets and test harnesses to validate model performance, robustness, and edge‑case behavior in real-world operational environments.
• Work closely with domain experts, software engineers, product managers, and research partners to translate complex Earth intelligence challenges into deployable AI solutions.
• Optimize models and inference systems for scalability, latency, cost efficiency, and reliability on modern cloud infrastructure.
• Implement and maintain production inference systems, including monitoring, model versioning, retraining workflows, and performance tracking.
• Stay current with the latest advances in foundation models, generative AI, multimodal learning, and reasoning systems, and translate research breakthroughs into practical systems.
• Maintain high engineering standards through code reviews, documentation, experimentation discipline, and collaborative problem solving.
• Help shape the next generation of Earth AI capabilities through collaboration with leading research organizations and technology partners.

• MS or PhD in Computer Science, Machine Learning, Artificial Intelligence, Applied Mathematics, or a related technical field, or equivalent practical experience.
• 5+ years of experience building and deploying machine learning systems in production environments.
• Demonstrated experience designing and delivering end-to-end ML pipelines, including data processing, training automation, evaluation frameworks, and scalable inference.
• Hands‑on experience developing and deploying deep learning models, particularly in one or more of the following areas:
• Vision‑language models (VLMs)
• Multimodal learning
• Reasoning models
• Large language models (LLMs)
• Computer vision or geospatial AI
• Strong programming skills in Python, with experience using modern ML frameworks such as PyTorch, Tensor Flow, or JAX.
• Experience building reproducible experimentation pipelines, including model evaluation, dataset versioning, and experiment tracking.
• Experience deploying models into production environments using modern cloud infrastructure and containerized systems.
• Familiarity with distributed training, large‑scale data processing, and model optimization techniques.
• Ability to collaborate across research, engineering, and product teams to bring advanced AI capabilities into real‑world applications.

• Experience working with geospatial data, remote sensing, satellite imagery, or Earth observation systems.
• Experience building or fine‑tuning foundation models, multimodal models, or agentic AI systems.
• Familiarity with Google Cloud Platform (GCP), including large‑scale AI/ML infrastructure.
• Experience implementing model monitoring, evaluation pipelines, and automated retraining systems.
• Contributions to open‑source AI projects,…