Computational Materials Scientist for Machine-Learned Interatomic Potentials (MD/DFT)

Amphiform; United States; On-site; USD 120,000 - 180,000; Full time

Job summary

Amphiform seeks a highly skilled computational scientist to lead its first atomistic simulation campaign. You will predict conductivity, hydration behavior, and interfacial transport in a novel hybrid material, coordinating with experimental teams.

The role spans DFT benchmarking, amorphous structure generation, MLIP development, and large-scale MD workflows. You will work directly with the experimental team to validate predictions, advance materials/processing development, and publish the

Qualifications

• PhD in computational chemistry, physics, or materials science.
• Hands-on ab-initio MD experience on HPC.
• Trained at least one machine-learned interatomic potential (MACE, NequIP, Allegro, DeepMD, GAP) and can explain how you built the training set and verified convergence.
• Strong scientific Python

Responsibilities

• Benchmark DFT functionals against references and manage error budgets.
• Build amorphous model structures of a hybrid metal-organic network.
• Fine-tune foundation MLIPs with active learning and run DFT labeling campaigns.
• Run nanosecond-scale transport MD, metadynamics, and PIMD for diffusion and activation energies.
• Translate simulation results into materials and process development decisions; publish methodology.
• Define simulation infrastructure, data management, and reproducibility

Skills

Python

ab-initio MD

MLIPs training

HPC experience

Education

PhD in computational chemistry/physics/materials science

Tools

MACE

NequIP

Allegro

DeepMD

GAP

psiflow

Parsl

Snakemake

Job description

Amphiform (amphiform.com) is building next‑gen energy materials for AI data centres, defence and space: light, abundant and powerful. We achieve that by creating a new type of matter: hybrid materials, built atomic layer by atomic layer, where every atom has a pre‑programmed purpose.

We just closed a $5.5+1m pre‑seed led by General Catalyst and Main Object, with Thomas Wolf (Hugging Face), Charlie Songhurst, and others.

The role:

We are developing a new class of material: an ultrathin, vapour‑deposited hybrid materials with custom properties - and we want to understand the fundamental properties. You will own our first atomistic simulation campaign: predicting conductivity (electron, ion, heat), hydration behaviour, and interfacial transport in a material that has never been simulated, and testing your predictions against experiments that we'll run constantly alongside. The workflow (DFT benchmarking → amorphous structure generation → fine‑tuned machine‑learned interatomic potentials with active learning → large‑scale transport MD, enhanced sampling, and path‑integral MD) is scoped, budgeted, and precedented in the recent literature; the material is not. You will be our first dedicated computational hire, working directly with the experimental team.

What you'll do:

• Benchmark DFT functionals against coupled‑cluster references for proton‑transfer energetics, and own the resulting error budget
• Build amorphous model structures of a hybrid metal‑organic network validated against our data
• Fine‑tune foundation MLIPs (MACE‑class) with active learning; run DFT labelling campaigns
• Run nanosecond‑scale transport MD, metadynamics, and PIMD to extract diffusion coefficients, activation energies, isotope effects, and interfacial behaviour
• Turn simulation into decisions: feed results into our materials and process development, and publish the methodology with us
• Define our simulation infrastructure (environments, data management, reproducibility)

What we're looking for:

• PhD in computational chemistry, physics, or materials science
• Hands‑on ab‑initio MD experience on HPC
• You have trained at least one machine‑learned interatomic potential (MACE, NequIP, Allegro, DeepMD, GAP, or similar) and can explain how you built the training set and knew it was converged
• Strong scientific Python

Nice to have:

• Ion transport background
• Path‑integral MD (i‑PI), GCMC (RASPA), charge‑partitioning workflows, or workflow engines (psiflow, Parsl, Snakemake)