Amazon Leo is looking to solve the problem of delivering fast, reliable internet connectivity to customers beyond the reach of existing networks by developing and deploying advanced science applications for their low Earth orbit satellite network.
Requirements
- 4+ years of deep learning, computer vision, human robotic interaction, algorithms implementation experience
- Experience in statistics methodology, applications to business problems or big data
- Experience with statistical methods (e.g., A/B Testing, Regression)
- Knowledge of one or more ML Frameworks (e.g., PyTorch, TensorFlow) and ML methods including NLP models (BERT, GPT-2/3), computer vision-based models (object detection, image recognition), and text-based models (Seq2Seq, Topic modeling)
- Experience with cloud computing technologies
- Knowledge of data structures, algorithm design, statistics, and system design
- Experience in calibration and anomaly detection
- Expert science/data science development experience in Python
Responsibilities
- Prototype, test, and implement state-of-the-art algorithms for antenna pointing calibration, anomaly detection, predictive failure models, and ground terminal performance evaluation
- Provide actionable recommendations for system design/definition by defining, running, and summarizing physically-accurate simulations of ground terminal functionality
- Collaborate closely with engineers to deploy performant, scalable, and maintainable applications in the cloud
- Design, implement, optimize, and operate systems critical to the uptime and performance of Leo ground terminals
- Design, development, deployment, and support of a Tier-1 Monitoring and Remediation System (MARS) needed to maintain high availability of hundreds of ground terminals deployed around the world
- Ground systems integration/test (I&T) automation
- Algorithm development (pointing/tracking/calibration/monitoring)
Other
- Master's degree or above in engineering, technology, computer science, machine learning, robotics, operations research, statistics, mathematics or equivalent quantitative field
- Candidates must be a U.S. citizen or national, U.S. permanent resident (i.e., current Green Card holder), or lawfully admitted into the U.S. as a refugee or granted asylum.
- Translate ambiguous problems into well defined mathematical problems
