Sr. Data Scientist
Amazon Bedrock
Amazon Web Services
Analytics
Artificial Intelligence
AWS
Aws Glue
Aws Sagemaker
Business Intelligence
Cloud
Cloud Computing
Cloud Data Warehouse
Cloud Operations
Cloud Platforms
Data
Data Analysis
Data Analytics
Data Architecture
Data Governance
Data Integration
Data Management
Data Observability
Data Platform
Data Processing
Data Science
Data Security
Data Visualization
Database
Databases
ETL
Graph Analytics
IT Services
Reporting and Analytics
Software Development
SQL
Time Series
Job Description
Context: Build observability and availability science for the Amazon Leo satellite broadband network, from research to production delivery.
Responsibilities
- Own observability and availability science end to end, including long-term vision, research roadmap, and production delivery, working backwards from customer, NOC, and network engineering needs.
- Develop time-series and graph-based models with dynamic baselining to detect network and ground-segment anomalies before they cross the High Severity threshold.
- Attribute cause automatically during live HSEs and LSEs by reasoning over multi-system telemetry, enabling Call Leaders and engineers to mitigate instead of hunting.
- Drive the science behind bucketed availability decomposition (geometric and satellite coverage, ground and network segments, customer terminals, payload, and planning), ensuring movements are attributed to true causes rather than noise.
- Deliver models, analyses, and metrics that feed daily system readiness and validation reviews consumed by senior leadership, linking availability and throughput to progress against GA entry criteria.
- Lead recurring fleet-wide “hot topic” investigations across ASIC, firmware, payload, network, and planning; separate correlated symptoms from root cause across thousands of nodes; quantify availability/throughput impact; assess whether a risk is launch-blocking and whether it is improving.
- Deliver alert correlation and deduplication, reduce false positives, and implement metric-quality scoring so responders trust system outputs and support a still-maturing KPI set.
- Connect models to measured organizational outcomes, including reducing detection and attribution time, raising availability against the network’s bar, and increasing the share of events prevented before customer impact.
- Partner day to day with the Network Operations Center, Network Engineering, and the Incident Management (Call Leader) program; join live HSE/LSE bridges and translate event learnings into model improvements.
- Feed COEs and RCAs back into detection and attribution to catch recurring signatures earlier; help design and score gamedays that stress-test both the network and the models against real, closed events.
- Build and deploy production pipelines on AWS (e.g., SageMaker, Bedrock, Glue) with model validation, monitoring, drift detection, and explainability so operations can trust model output under pressure.
- Set data-science standards, mentor scientists, and drive best practices across the Leo networking organization as the science function scales.
- Produce explainable outputs and written narratives that allow responders and leaders three or more levels up to act on models during and between events.
Requirements
- 5+ years of experience with data querying languages (e.g., SQL), scripting languages (e.g., Python), or statistical/mathematical software (e.g., R, SAS, Matlab, etc.).
- 4+ years of experience as a data scientist.
- Experience with statistical models, including multinomial logistic regression.
Technologies
- SQL
- Python
- R
- SAS
- Matlab
- multinomial logistic regression
- AWS QuickSight
- Tableau
- R Shiny
- AWS
- SageMaker
- Bedrock
- Glue
Preferred Qualifications
- 2+ years of data visualization experience using AWS QuickSight, Tableau, R Shiny, etc.
- Experience managing data pipelines.
- Experience leading and mentoring on a data science team.
Benefits
- Health insurance (medical, dental, vision, prescription), Basic Life & AD&D, and option for Supplemental life plans
- EAP and Mental Health Support
- Medical Advice Line
- Flexible Spending Accounts
- Adoption and Surrogacy Reimbursement coverage
- 401(k) matching
- Paid time off
- Parental leave
- Sign-on payments
- Restricted stock units (RSUs)
Export Control Requirement
Due to applicable export control laws and regulations, candidates must be a U.S. citizen or national, a U.S. permanent resident (current Green Card holder), or lawfully admitted into the U.S. as a refugee or granted asylum.
A Day in the Life
- Review overnight anomaly detections and availability movements.
- Join an HSE bridge as the science partner.
- Refine root-cause attribution models or present availability findings at the readiness review.
About the Team
- Amazon Leo Networking Software builds and operates the software behind Leo’s satellite and ground network.
- The science function partners with the NOC, Network Engineering, and Incident Management to improve availability and resilience.
- Work shifts from reacting to outages to predicting and preventing them.
- As a Data Scientist III, help shape the science function as it grows.