SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
SandboxAQ is seeking a Staff Materials Research Scientist to lead PFAS alternative discovery efforts within its Chemical Simulation (ChemSim) group. This role bridges AI-driven generative chemistry discovery with industrial validation partners in semiconductor manufacturing.
You will own the partner-facing validation loop, serving as the primary scientific contact with co-development partners (chemical suppliers, equipment makers, control/sensor companies) to define problems, target specifications, constraints, and qualification criteria. You will operate SandboxAQ's generative chemistry discovery workflow for PFAS-substitution use cases, assess predicted compounds for chemical plausibility and fit, and rank them to produce decision-ready shortlists for experimental validation.
Key responsibilities include: applying semiconductor domain judgment to evaluate whether generative and simulation outputs are directionally correct for target applications; validating lead molecules against real-world semiconductor process, performance, and environmental/health/safety constraints; translating partner validation results and experimental data into actionable technical improvement points for internal teams; and aligning targets across internal dataset, computational chemistry, machine-learning, and generative-modeling teams.
Required qualifications: PhD in Chemistry, Chemical Engineering, Materials Science, or related field with deep specialization in semiconductor process materials and/or fluorochemistry. 6+ years of post-PhD industrial or applied R&D experience developing, formulating, or qualifying semiconductor process chemicals, including direct hands-on experience discovering or evaluating PFAS-lean/PFAS-free alternatives for semiconductor manufacturing and adjacent materials (wet-etch/clean chemistries, lithography materials, heat-transfer fluids, immersion cooling fluids). Working knowledge of semiconductor unit processes (lithography, etch, CMP, cleaning, thermal management) and their performance and EHS specifications. Demonstrated ability to lead application-driven engagements with external industrial partners and translate between experimental results and computational/modeling requirements. Proficiency in Python to run and configure computational discovery workflows and interpret outputs. Familiarity with generative molecular design, high-throughput virtual screening, or ML property prediction for molecules and materials.
