Apply on Employer Site

Blue Origin · 3 hours ago

Thermal Protection System Materials Informatics Engineer

Greater Seattle Area

Full-time

Onsite

New Grad, Entry Level

$121K/yr - $169K/yr

Blue Origin is working towards developing reusable, safe, and low-cost space vehicles and systems. The Thermal Protection System Materials Informatics Engineer role involves developing data-driven models and workflows to enhance thermal protection system materials and processes, leveraging knowledge in materials science and machine learning.

AerospaceManufacturingNational SecurityRenewable Energy

No H1B

U.S. Citizen Only

Responsibilities

Develop and apply data‑driven models

Build and evaluate surrogate models (e.g., regression, Gaussian Processes, neural networks) to predict key TPS material properties and performance metrics from composition, processing, and test conditions

Support implementation of Bayesian optimization or related methods to propose new material compositions, processes, or test conditions

Collect, clean, and organize TPS materials data from experiments, simulations, and literature into structured datasets suitable for analysis and ML

Perform exploratory data analysis to identify trends, correlations, and data gaps that inform future testing and development plans

Work with TPS materials and process engineers to translate known design rules, constraints, and operating environments (e.g., re‑entry conditions) into model features, priors, and search‑space constraints

Help encode empirical and physics‑based relationships (e.g., degradation mechanisms, thermal response trends) into models and analysis workflows

Partner with experimental and manufacturing teams to design data‑driven screening and development plans, interpret model results, and incorporate new data into the modeling workflows

Prepare clear plots, reports, and presentations to communicate findings and recommendations to cross‑functional stakeholders

Maintain and improve analysis scripts, Jupyter notebooks, and related tools; follow good software practices (version control, documentation)

Stay current with developments in materials informatics and ML for scientific discovery and help bring relevant methods into the TPS development workflow

Qualification

Materials ScienceMachine LearningData AnalysisPythonHigh-temperature materialsSurrogate modelingVersion controlJupyter notebooksLinux/HPC environmentsCommunication skillsTeam collaboration

Required

Bachelor's degree in Materials Science and Engineering or other relevant fields (e.g., Ceramic Engineering, Metallurgical Engineering, Mechanical Engineering, Chemical Engineering, Applied Physics); OR Bachelor's degree in Computer Science, Data Science, Electrical Engineering, or related field with demonstrated exposure to materials or physical sciences

Familiarity with structure–processing–property relationships in materials

Exposure to high‑temperature materials, thermal protection systems, ceramics, composites, or related domains through coursework, projects, research, or internships

Ability to read and interpret technical materials literature (e.g., property data, degradation mechanisms, processing–microstructure relationships)

Proficiency in Python for scientific computing and data analysis (e.g., numpy, pandas, matplotlib or similar)

Hands‑on experience with at least one machine learning or data‑analysis library (e.g., scikit‑learn, PyTorch, TensorFlow, or similar) from coursework, projects, or research

Working understanding of basic ML concepts: regression, training/validation splits, overfitting/underfitting, and model evaluation metrics

Strong written and verbal communication skills; ability to explain technical topics to audiences

In‑depth knowledge or expertise in at least ONE of the following areas: Application of machine learning or advanced data analysis to materials, chemistry, or other physical science problems; High‑temperature materials or TPS materials and their performance/degradation mechanisms; Handling and interpreting complex experimental or simulation datasets (e.g., multi‑parameter test matrices, time‑dependent response data, or multi‑fidelity data from experiments and modeling)

Preferred

Advanced degree (M.S. or Ph.D., completed or in progress) in Materials Science & Engineering or related field, particularly with a focus on materials informatics or data‑driven materials design

Hands‑on experience with Gaussian Process Regression or other probabilistic models

Bayesian optimization, active learning, or sequential design of experiments

Neural network models (e.g., feed‑forward NNs, graph neural networks, or physics‑informed neural networks) for surrogate modeling of physical systems

Experience with TPS materials screening, down‑selection, or development for re‑entry or similar extreme environments

Materials modeling tools or data (e.g., finite element thermal/structural models, DFT/MD/CALPHAD outputs)

Familiarity with version control (e.g., Git) and collaborative code development

Jupyter notebooks or similar tools for reproducible analysis and reporting

Linux/HPC environments or GPU‑accelerated workflows

Hands‑on experience taking a materials or process concept from ideation through test and into hardware (e.g., senior design projects, research, or prior roles)