Software Engineer , Data Science; New Grad

Space is a war fighting domain. True Anomaly seeks those with the talent and ambition to build the technology that secures it.

True Anomaly delivers decisive capabilities for space superiority. We build autonomous spacecraft, advanced payloads, mission software, and space-based interceptors — enabling the U.S. and its Allies to secure the space environment and counter threats from the ultimate high ground.

• Be the offset. We create asymmetric advantages with creativity and ingenuity.
• What would it take? We challenge assumptions to deliver ambitious results.
• It’s the people. Our team is our competitive advantage and we are better together.

You’ll turn spacecraft data into actionable insights across manufacturing and operations: building dashboards that surface production bottlenecks and on-orbit anomalies, analyzing test failures and mission telemetry to identify root causes, training predictive models that flag at‑risk components before integration and detect spacecraft health degradation during missions, and mining telemetry to catch anomalies operators would miss. Your work spans the full spacecraft lifecycle.

Pre-launch, you’ll analyze manufacturing telemetry, test logs, failure reports, and supplier data to catch problems before integration. Post-launch, you’ll monitor on-orbit telemetry streams, detect anomalies in spacecraft health data, analyze mission performance, and flag degradation patterns that predict future failures. This is entry-level data science work supporting hardware production and spacecraft operations. You’ll write SQL queries, build predictive models in Python, create operational dashboards, and see your analysis drive decisions on the manufacturing floor and in mission control.

This is a 3 month temporary employment engagement. There is potential to convert to regular employment based on performance and business need.

• Perform exploratory data analysis on manufacturing telemetry, test logs, mission data, and on-orbit spacecraft health telemetry to identify patterns and surface anomalies.
• Build operational dashboards in Grafana or Plotly Dash showing real-time production status, spacecraft health metrics, mission performance, and anomaly alerts.
• Train basic predictive models (logistic regression, random forests) to flag at-risk components during manufacturing and predict spacecraft health degradation during missions.
• Write SQL queries to extract, join, and aggregate data from manufacturing databases, test systems, mission telemetry streams, and spacecraft health archives.
• Analyze test failures and on-orbit anomalies to identify common failure modes, cluster similar issues, and quantify impact on schedule and mission success.
• Create data visualizations (matplotlib, seaborn, Plotly) that communicate findings to engineers, manufacturing leads, mission operators, and program managers.
• Implement statistical process control charts to detect out-of-spec conditions in manufacturing processes and spacecraft telemetry before they cascade.
• Monitor on-orbit telemetry streams for anomalies: battery voltage trends, thermal behavior, attitude control health, communications link quality.
• Document analysis methodology in Jupyter notebooks enabling reproducibility and knowledge transfer across manufacturing and operations teams.
• Learn reliability engineering and mission operations concepts: failure modes, burn-in testing, on-orbit commissioning, spacecraft health monitoring, and anomaly response procedures.

• Bachelor's or Master's degree in data science, statistics, industrial engineering, applied mathematics, operations research, or related quantitative field.
• Proficiency in Python for data analysis: pandas, numpy, matplotlib, seaborn.
• Working knowledge of SQL for querying relational databases: SELECT, JOIN, GROUP BY, aggregation functions.
• Coursework in statistics: hypothesis testing, regression, probability distributions, experimental design.
• Ability to create clear visualizations that communicate insights to technical and non-technical audiences.
• Strong curiosity about how things fail and how data can predict failures before they happen.
• Debugg…