AI Engineer III - Blue Ring

About the role

The role is part of the In-Space Systems business unit, which is focused on addressing two of the most compelling challenges in spaceflight today: space infrastructure and increasing mobility on-orbit. Blue Ring is Blue Origin's multi-mission space mobility platform, and this team is building the next generation of intelligent ground systems that will redefine how satellite fleets are operated—moving beyond manual monitoring and reactive processes.

Responsibilities

• Multi-Agent System Development
• Implement and optimize multi-agent systems that coordinate across telemetry analysis, anomaly detection, flight dynamics, and mission planning domains
• Build and maintain agent orchestration frameworks that integrate with LLM services and ground system services for reliable agent execution with observability and memory
• Develop and deploy RAG pipelines over flight manuals, operations procedures, design documents, and historical log files
• Manage vector database infrastructure, embedding pipelines, and retrieval strategies to deliver accurate answers to operator queries
• Implement human-in-the-loop decision workflows where agents present investigation plans and remediation options for operator approval
• Develop confidence scoring and validation systems for AI recommendations
• Deploy containerized AI services on AWS with infrastructure-as-code, CI/CD pipelines, observability, and automated testing
• Support on-call rotations and drive root-cause analysis for production issues
• Model Development (Post-training and Time-series Analysis)
• Develop anomaly detection models that identify telemetry deviations beyond threshold-based monitoring
• Train and deploy sequence-based models for failure prediction on telemetry data
• Build automated model retraining pipelines that incorporate operator feedback and new flight data
• Explore compressed models for resource-constrained deployment scenarios

Requirements

• Able to work onsite in one of our Kent, WA, Renton, WA, or Reston, VA offices.
• Bachelor's or Master's degree in Computer Science, Machine Learning, Electrical Engineering, or a related field.
• 5+ years of professional software development experience with a focus on AI/ML applications in production environments.
• Proficiency in Python and at least one AI/ML framework (PyTorch, TensorFlow).
• Hands-on experience building and deploying multi-agent systems, agentic AI workflows, or LLM-based applications in production.
• Experience designing and operating RAG pipelines, including vector databases, embedding models, and retrieval strategies.
• Experience with time-series ML models (RNNs, LSTMs, Transformers) for anomaly detection or forecasting on sensor/telemetry data.
• Experience with cloud platforms (AWS preferred), containerization (Docker, Kubernetes), and CI/CD pipeline implementation.
• Knowledge of professional software engineering practices including code reviews, source control, automated testing, and operational excellence.
• Strong analytical and problem-solving skills with attention to detail.
• Excellent written and verbal communication skills for documentation and cross-team collaboration.

Qualifications

• Able to work onsite in one of our Kent, WA, Renton, WA, or Reston, VA offices.
• Bachelor's or Master's degree in Computer Science, Machine Learning, Electrical Engineering, or a related field.
• 5+ years of professional software development experience with a focus on AI/ML applications in production environments.
• Proficiency in Python and at least one AI/ML framework (PyTorch, TensorFlow).
• Hands-on experience building and deploying multi-agent systems, agentic AI workflows, or LLM-based applications in production.
• Experience designing and operating RAG pipelines, including vector databases, embedding models, and retrieval strategies.
• Experience with time-series ML models (RNNs, LSTMs, Transformers) for anomaly detection or forecasting on sensor/telemetry data.
• Experience with cloud platforms (AWS preferred), containerization (Docker, Kubernetes), and CI/CD pipeline implementation.
• Knowledge of professional software engineering practices including code reviews, source control, automated testing, and operational excellence.
• Strong analytical and problem-solving skills with attention to detail.
• Excellent written and verbal communication skills for documentation and cross-team collaboration.

Skills

• Deep expertise across the full AI/ML development lifecycle.
• Building multi-agent systems and retrieval-augmented generation pipelines.
• Training and deploying time-series ML models on real spacecraft telemetry.
• Human-in-the-loop decision workflows.
• Confidence scoring and validation systems for AI recommendations.
• Containerized AI services on AWS with infrastructure-as-code, CI/CD pipelines, observability, and automated testing.
• On-call rotations and drive root-cause analysis for production issues.
• Model development and deployment.
• Automated model retraining pipelines.
• Vector database infrastructure management.
• Embedded pipelines and retrieval strategies.
• Human-in-the-loop decision workflows.
• Confidence scoring and validation systems for AI recommendations.
• Containerized AI services on AWS with infrastructure-as-code, CI/CD pipelines, observability, and automated testing.
• On-call rotations and drive root-cause analysis for production issues.
• Model development and deployment.
• Automated model retraining pipelines.
• Vector database infrastructure management.
• Embedded pipelines and retrieval strategies.
• Human-in-the-loop decision workflows.
• Confidence scoring and validation systems for AI recommendations.
• Containerized AI services on AWS with infrastructure-as-code, CI/CD pipelines, observability, and automated testing.
• On-call rotations and drive root-cause analysis for production issues.
• Model development and deployment.
• Automated model retraining pipelines.
• Vector database infrastructure management.
• Embedded pipelines and retrieval strategies.
• Human-in-the-loop decision workflows.
• Confidence scoring and validation systems for AI recommendations.
• Containerized AI services on AWS with infrastructure-as-code, CI/CD pipelines, observability, and automated testing.
• On-call rotations and drive root-cause analysis for production issues.
• Model development and deployment.
• Automated model retraining pipelines.
• Vector database infrastructure management.
• Embedded pipelines and retrieval strategies.
• Human-in-the-loop decision workflows.
• Confidence scoring and validation systems for AI recommendations.
• Containerized AI services on AWS with infrastructure-as-code, CI/CD pipelines, observability, and automated testing.
• On-call rotations and drive root-cause analysis for production issues.
• Model development and deployment.
• Automated model retraining pipelines.
• Vector database infrastructure management.
• Embedded pipelines and retrieval strategies.
• Human-in-the-loop decision workflows.
• Confidence scoring and validation systems for AI recommendations.
• Containerized AI services on AWS with infrastructure-as-code, CI/CD pipelines, observability, and automated testing.
• On-call rotations and drive root-cause analysis for production issues.
• Model development and deployment.
• Automated model retraining pipelines.
• Vector database infrastructure management.
• Embedded pipelines and retrieval strategies.
• Human-in-the-loop decision workflows.
• Confidence scoring and validation systems for AI recommendations.
• Containerized AI services on AWS with infrastructure-as-code, CI/CD pipelines, observability, and automated testing.
• On-call rotations and drive root-cause analysis for production issues.
• Model development and deployment.
• Automated model retraining pipelines.
• Vector database infrastructure management.
• Embedded pipelines and retrieval strategies.
• Human-in-the-loop decision workflows.
• Confidence scoring and validation systems for AI recommendations.
• Containerized AI services on AWS with infrastructure-as-code, CI/CD pipelines, observability, and automated testing.
• On-call rotations and drive root-cause analysis for production issues.
• Model development and deployment.
• Automated model retraining pipelines.
• Vector database infrastructure management.
• Embedded pipelines and retrieval strategies.
• Human-in-the-loop decision workflows.
• Confidence scoring and validation systems for AI recommendations.
• Containerized AI services on AWS with infrastructure-as-code, CI/CD pipelines, observability, and automated testing.
• On-call rotations and drive root-cause analysis for production issues.
• Model development and deployment.
• Automated model retraining pipelines.
• Vector database infrastructure management.
• Embedded pipelines and retrieval strategies.
• Human-in-the-loop decision workflows.
• Confidence scoring and validation systems for AI recommendations.
• Containerized AI services on AWS with infrastructure-as-code, CI/CD pipelines, observability, and automated testing.
• On-call rotations and drive root-cause analysis for production issues.
• Model development and deployment.
• Automated model retraining pipelines.
• Vector database infrastructure management.
• Embedded pipelines and retrieval strategies.
• Human-in-the-loop decision workflows.
• Confidence scoring and validation systems for AI recommendations.
• Containerized AI services on AWS with infrastructure-as-code, CI/CD pipelines, observability, and automated testing.
• On-call rotations and drive root-cause analysis for production issues.
• Model development and deployment.
• Automated model retraining pipelines.
• Vector database infrastructure management.
• Embedded pipelines and retrieval strategies.
• Human-in-the-loop decision workflows.
• Confidence scoring and validation systems for AI recommendations.
• Containerized AI services on AWS with infrastructure-as-code, CI/CD pipelines, observability, and automated testing.
• On-call rotations and drive root-cause analysis for production issues.
• Model development and deployment.
• Automated model retraining pipelines.
• Vector database infrastructure management.
• Embedded pipelines and retrieval strategies.
• Human-in-the-loop decision workflows.
• Confidence scoring and validation systems for AI recommendations.
• Containerized AI services on AWS with infrastructure-as-code, CI/CD pipelines, observability, and automated testing.
• On-call rotations and drive root-cause analysis for production issues.
• Model development and deployment.
• Automated model retraining pipelines.
• Vector database infrastructure management.
• Embedded pipelines and retrieval strategies.
• Human-in-the-loop decision workflows.
• Confidence scoring and validation systems for AI recommendations.
• Containerized AI services on AWS with infrastructure-as-code, CI/CD pipelines, observability, and automated testing.
• On-call rotations and drive root-cause analysis for production issues.
• Model development and deployment.
• Automated model retraining pipelines.
• Vector database infrastructure management.
• Embedded pipelines and retrieval strategies.
• Human-in-the-loop decision workflows.
• Confidence scoring and validation systems for AI recommendations.
• Containerized AI services on AWS with infrastructure-as-code, CI/CD pipelines, observability, and automated testing.
• On-call rotations and drive root-cause analysis for production issues.
• Model development and deployment.
• Automated model retraining pipelines