Staff Research Scientist, Catalyst Simulation

SandboxAQ

1d•$163,200 - $306,000•Hybrid

About The Position

SandboxAQ is seeking a Staff Research Scientist, Catalyst Simulation to join their Catalysis team. This role involves leading the translation of reaction energetics from simulations and machine learning into process-scale predictions for industrial applications. The Catalysis team focuses on developing and validating new catalyst technologies for high-purity chemical production, emissions treatment, and advanced sensing, using a combination of computational modeling, machine learning, and experimental validation. The ideal candidate will own the design and execution of microkinetic and reactor-level modeling workflows, connect atomistic simulation outputs to performance predictions, collaborate with industrial partners, and mentor junior scientists. This is an opportunity to shape the technical roadmap for microkinetic modeling at SandboxAQ and contribute to advancing catalyst technologies from discovery to real-world use.

Requirements

PhD in Chemical Engineering, Chemistry, Materials Science, or a related field, with deep specialization in microkinetic modeling, surface reaction engineering, or multi-scale catalysis simulation.
6+ years of post-PhD experience (or equivalent) building and applying microkinetic models in an industrial or applied R&D context, including coupling atomistic energetics to reactor-level predictions.
Strong publication or patent record demonstrating expertise across DFT-derived energetics, microkinetic modeling, and reactor-scale integration.
Proficient in Python and modern scientific software practices in an HPC environment; comfortable working with ML-trained force fields and foundation models as inputs to kinetic workflows.
Demonstrated ability to lead application-driven scientific engagements with external industrial partners and to communicate results to non-specialist audiences.
Must be a US Person (Permanent Resident or Citizen) due to U.S. Government contractual requirements.

Nice To Haves

Direct experience with semiconductor-relevant catalytic chemistries.
Experience with operando or in-situ characterization data and using it to calibrate microkinetic models.
Familiarity with Bayesian optimization, active learning, or uncertainty quantification applied to catalyst discovery.
Experience operating in a CHIPS Act or other federally funded R&D program.

Responsibilities

Design, build, and own microkinetic and reactor-level modeling workflows that translate energetics derived from atomistic simulations and machine learning potentials into process-scale observables for complex catalytic and specialty chemical synthesis processes.
Lead application engagements with industrial partners (e.g., specialty chemical manufacturers, equipment providers, and process technology developers), translating partner problems into well-posed modeling targets and delivering credible, decision-ready results.
Partner closely with internal dataset, computational chemistry, and machine learning teams to specify the energetics, descriptors, and uncertainty estimates microkinetic workflows require, closing the loop between reaction-scale and process-scale modeling.
Validate models against experimental data from scientific and academic partners; drive iterative model refinement and uncertainty quantification.
Mentor junior research and computational scientists; contribute to publications, partner deliverables, and the technical roadmap for microkinetic modeling capabilities within SandboxAQ.