Apply on Employer Site

SandboxAQ · 4 months ago

Postdoctoral Researcher - Machine Learning for Materials & Alloys

United States

Full-time

Remote

New Grad, Entry Level

$115K/yr - $125K/yr

SandboxAQ is a high-growth company delivering AI solutions that address some of the world's greatest challenges. They are seeking a motivated postdoctoral researcher to develop and apply machine learning methods at the intersection of materials science and structural design, focusing on data-driven approaches and optimization techniques to support engineering workflows and decision-making.

Artificial Intelligence (AI)Cyber SecurityInformation TechnologyQuantum ComputingSaaS

No H1B

U.S. Citizen Only

Responsibilities

Develop and apply ML and optimization techniques to guide lightweighting strategies

Use reasoning-based ML approaches to evaluate trade-offs among performance, manufacturability and other criteria

Apply Bayesian optimization and related uncertainty-aware methods to balance performance, manufacturability, and other constraints

Build reproducible workflows that integrate materials data, manufacturing methods, and simulation outputs

Curate and analyze structured datasets on materials, processing routes, and mechanical properties to support ML pipelines

Collaborate with engineers and computer scientists to connect ML outputs with structural and materials design tasks

Write technical reports and present results to technical and non-technical stakeholders

Qualification

Machine LearningBayesian OptimizationPythonMaterials ScienceStatistical MethodsProblem-solvingCommunication SkillsCollaboration

Required

U.S. citizenship is required due to USG contract requirements

PhD in Materials Science, Metallurgy, Mechanical Engineering, Computational Materials Science, Applied Physics, or a related field

Demonstrated experience applying ML or statistical methods to materials or engineering applications

Proficiency in Python and ML frameworks (PyTorch, TensorFlow, Scikit-learn)

Familiarity with optimization and uncertainty quantification methods such as Bayesian optimization, Gaussian processes, ensemble learning, or related approaches

Strong research track record, evidenced by publications in materials science, ML, or computational design

Excellent problem-solving and communication skills

Preferred

Familiarity with knowledge graphs or graph-based ML for materials/manufacturing data

Experience with LLMs for data integration, retrieval-augmented reasoning, or decision support

Experience with graph-based, generative, or physics-informed ML for materials or engineering applications

Background in lightweighting, alloy substitutions, or design for manufacturability

Experience working with experimental or simulation-based datasets in materials (e.g., thermomechanical processing data, microstructure characterization, or finite element modeling)

Ability to work collaboratively in multidisciplinary teams