Force Field Developer — Physics and ML Driven Models for Biomolecular Simulation

If you have ever stared at a failed molecular dynamics simulation and suspected the underlying force field was the silent culprit, this role is built entirely around fixing that exact pain point. You will be bridging quantum-level physics and machine learning to build high-precision models that directly dictate how future therapeutics are designed. It is a rare chance to move past standard off-the-shelf parameters and actually advance the predictive power of computational drug discovery.

What You'll Actually Be Doing

Your day-to-day will involve designing novel parameterization strategies, combining traditional physics-based molecular interactions with modern machine learning architectures. You will spend a good chunk of your time deriving parameters for ligands and small molecules, validating those force fields against rigorous benchmarks, and running massive simulations on specialized hardware to see how your models behave under real-world pressure. You will also sit down with the drug discovery team to translate your modeling choices into actionable insights for their active pipelines.

The Core Tech Stack

You need a rock-solid foundation in physical chemistry, biophysics, or chemical physics combined with fluency in machine learning methods applied to molecular systems. Experience with physics-based force field development, small molecule parameterization, and handling large-scale simulation infrastructure is non-negotiable. The team relies on this deep intersection of physics and ML to squeeze every ounce of accuracy out of their high-speed commodity computing and specialized hardware.

Interview Expectations

Expect the interviewers to drop you straight into a deep architectural debate about handling charge transfer or polarization limits in traditional force fields versus neural network potentials. They want to see how you troubleshoot a force field that blows up during a protein-ligand unbinding simulation. The hiring manager is secretly testing whether you can balance rigorous thermodynamic theory with pragmatic engineering choices when the ML model starts hallucinating unphysical atomic geometries.

Application Advice

Your resume needs to heavily feature your Ph.D. or concrete research contributions in computational chemistry, force field construction, or molecular machine learning. Ditch the generic summaries and explicitly call out terms like parameterization strategies, ligand modeling, and validation metrics. If you have published papers or open-source contributions showing you can tame messy molecular data, put them right at the top.