Applied Scientist, Amazon Leo Satellite Build Systems

Description

Build the scientific intelligence layer powering Amazon’s satellite manufacturing system. As an Applied Scientist, you will develop machine learning models that transform fragmented manufacturing, test, quality, and operational data into actionable intelligence that improves how satellites are built.

Build the scientific intelligence layer powering Amazon’s satellite manufacturing system. As an Applied Scientist, you will develop machine learning models that transform fragmented manufacturing, test, quality, and operational data into actionable intelligence that improves how satellites are built.

You will tackle ambiguous, high-impact problems where data is incomplete, noisy, and distributed, and where model outputs influence real-world manufacturing decisions. Your work will power AI-enabled workflows such as non-conformance disposition, root-cause analysis, and predictive test optimization - reducing defects, accelerating production, and helping create more intelligent, data-driven manufacturing systems.

Export Control Requirement:
Due to applicable export control laws and regulations, 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 manufacturing and operational problems into well-defined scientific problems, modeling approaches, and evaluation criteria
• Design, train, and deploy machine learning models, including LLM-based systems, retrieval models, and task-specific models
• Develop and evaluate models using large-scale, noisy, heterogeneous datasets with incomplete, delayed, or imperfect ground truth
• Apply state-of-the-art techniques in areas such as anomaly detection, root-cause inference, multimodal learning, information retrieval, and generative AI, adapting or extending them to meet project requirements
• Design experiments and evaluation frameworks that capture real-world failure modes, distribution shift, and decision risk
• Make principled tradeoffs among model complexity, data quality, accuracy, latency, cost, and maintainability
• Build production-quality scientific components with appropriate testing, documentation, monitoring, and operational mechanisms
• Work with Manufacturing, Quality, Test, and engineering partners to understand customer needs and translate them into effective scientific solutions
• Analyze model and system performance, identify gaps and root causes, and iteratively improve deployed solutions
• Clearly document scientific approaches, experimental results, design decisions, and lessons learned so that others can understand and reproduce the work
• Contribute to technical discussions, mentor less experienced teammates, and help advance scientific and engineering best practices within the team

You may start by partnering with Quality and Manufacturing teams to define a training dataset for a root-cause prediction model, including how historical cases should be labeled and evaluated. You then design experiments and train models, comparing approaches across architectures, features, and data slices. Later, you analyze benchmark results to identify failure modes, data-quality issues, and generalization gaps, and refine the evaluation set to better represent real-world cases.

You work with engineers to integrate the model into a production workflow, adding testing, monitoring, and feedback mechanisms. Throughout the day, you balance scientific rigor with practical constraints such as data availability, latency, reliability, and operational cost.

Leo Satellite Build Systems is the centralized AI team within Leo Production Operations. We build shared capabilities for AI across Production Operations, including governed data assets, machine learning models, retrieval systems, evaluation frameworks, and knowledge services. We work on real-world systems where scientific decisions can influence physical outcomes. We value rigorous experimentation, strong data foundations, clear documentation, and production-ready engineering. Our team is helping enable AI-native manufacturing by turning fragmented operational knowledge and data into reliable intelligence that improves production outcomes.

• 3+ years of building models for business application experience
• PhD, or Master's degree and 4+ years of CS, CE, ML or related field experience
• Experience in patents or publications at top-tier peer-reviewed conferences or journals
• Experience programming in Java, C++, Python or related language
• Experience in any of the following areas: algorithms and data structures, parsing, numerical optimization, data mining, parallel and distributed computing, high-performance computing

• Experience using Unix/Linux
• Experience in professional software development
• - Experience with one or more areas such as natural language processing, information retrieval, multimodal learning, anomaly…