YOUR MISSION
You'll build predictive models that catch component failures before they impact missions by analyzing manufacturing telemetry, deploy real-time anomaly detection systems for testing and operations that flag deviations operators would miss, and investigate schedule slips and quality issues using data-driven root cause analysis to distinguish signal from noise. You'll mine historical production data to identify bottlenecks, optimize test durations, and reduce rework, while scoring supplier reliability and predicting delivery delays to flag at-risk components. Throughout, you'll develop integrated diagnostic tools that fuse logs, telemetry, and historical data to narrow failure root causes and accelerate engineering investigations that keep spacecraft on schedule and missions on track.
RESPONSIBILITIES- Build predictive models for component failure prediction using manufacturing telemetry, test data, and historical reliability records to catch issues before they impact missions
- Design and deploy anomaly detection systems for launch operations, environmental testing, and spacecraft integration that flag deviations in real-time without overwhelming operators with false alarms
- Perform root cause analysis on schedule delays, test failures, and quality escapes using causal inference, data mining, and statistical modeling to identify actionable improvement opportunities
- Develop data-driven diagnostic systems that fuse manufacturing history, supplier data, test logs, and failure reports to narrow root causes and accelerate troubleshooting
- Build and maintain operational dashboards providing real-time situational awareness across production, test, and integration workflows
- Mine historical test and production data to identify patterns, cluster failure modes, prioritize process improvements, and quantify risk for upcoming builds
- Implement statistical process control and quality monitoring systems that detect out-of-spec conditions before they propagate downstream
- Write clear, maintainable Python/SQL code and Jupyter notebooks that document analysis methodology and enable reproducibility across the engineering team
- Learn and grow alongside operations, manufacturing, and reliability engineers, translating business questions into data solutions that drive decisions
QUALIFICATIONS- Bachelor's degree in data science, statistics, industrial engineering, applied mathematics, operations research, or a similar quantitative discipline, plus 2-4 years of experience; or a Master's degree in one of these fields with no experience required.
- Proficient in Python (pandas, scikit-learn, matplotlib) and SQL for data manipulation, analysis, and visualization
- Strong statistical fundamentals: hypothesis testing, regression, time-series analysis, survival analysis, and experimental design
- Experience building end-to-end data pipelines: data cleaning, feature engineering, model training, validation, and deployment
- Ability to communicate technical findings to non-technical stakeholders through clear visualizations and actionable recommendations
- Eagerness to learn manufacturing, operations, and reliability engineering domains where data science drives real operational improvements
- Passion for spaceflight and building reliable systems that perform in high-stakes environments
PREFERRED SKILLS AND EXPERIENCE- Experience with reliability engineering: survival analysis (Weibull, Cox models), reliability growth modeling, failure mode analysis
- Familiarity with manufacturing analytics: statistical process control (SPC), multivariate control charts, quality prediction from process data
- Exposure to anomaly detection techniques: Isolation Forest, LSTM autoencoders, change point detection, multivariate process monitoring
- Internship, research, or project experience in operations analytics, supply chain forecasting, or industrial IoT telemetry analysis
- Understanding of causal inference methods: directed acyclic graphs (DAGs), counterfactual reasoning, confounding variable analysis
- Experience with imbalanced classification: SMOTE, cost-sensitive learning, active learning for rare event prediction
- Familiarity with time-series forecasting: ARIMA, Prophet, exponential smoothing, handling regime changes and structural breaks
- Coursework or project work in operations research, queuing theory, optimization, or discrete event simulation
- Experience with text mining and NLP for log analysis, failure report clustering, or automated fault diagnosis
COMPENSATION- Base Salary: $125,000 - 270,000
- Equity + Benefits including Health, Dental, Vision, HRA/HSA options, PTO and paid holidays, 401K, Parental Leave
Your actual level and base salary will be determined on a case-by-case basis and may vary based on the following considerations: job-related knowledge and skills, education, location, and experience.
ADDITIONAL REQUIREMENTS- Work Location-this is a fully onsite role. Candidates must be based in or able to commute to our Denver or Long Beach office daily.
- Work environment-the work environment; temperature, noise level, inside or outside, or other factors that will affect the person's working conditions while performing the job.
- Physical demands-the physical demands of the job, including bending, sitting, lifting and driving.
This position will be open until it is successfully filled. To submit your application, please follow the directions below. #LI-Onsite
