Scientist II / Senior ML Scientist, Cofolding and Structure-Aware ML

Lila Sciences•Cambridge, MA

11d•$228,000 - $358,000

About The Position

Lila Sciences is seeking a Machine Learning Scientist, Cofolding and Structure-Aware ML to train next-generation cofolding models for drug discovery. This role is focused on improving models that reason over proteins, ligands, binding context, and experimental data, potentially using contrastive learning and related representation-learning approaches. This person should have direct experience training modern scientific ML models, not only using pretrained systems. You will work with ML researchers, computational chemists, computational biophysicists, data engineers, and drug discovery teams to develop models that learn from DEL and related datasets, connect molecular and protein context, and improve AI-driven discovery decisions. The models developed in this role should produce outputs that medicinal and computational chemists as well as biophysicists can interrogate, validate, and use in downstream agent-driven discovery decisions.

Requirements

PhD or equivalent experience in machine learning, computational biology, computational chemistry, bioinformatics, computer science, or a related field.
Hands-on experience training deep learning models for molecular, protein, structural biology, or scientific data applications.
Experience with contrastive learning, representation learning, self-supervised learning, or multimodal learning.
Familiarity with DEL or related selection, enrichment, screening, or molecular assay datasets.
Experience with protein-ligand modeling, cofolding, structure prediction, geometric deep learning, or structure-aware molecular ML.
Practical experience with PyTorch, JAX, or an equivalent ML framework.
Ability to design careful experiments, ablations, and evaluations for scientific ML models.
Strong understanding of data quality, leakage risks, negative construction, and benchmark design.
Ability to collaborate across ML, data, computational science, and drug discovery functions.

Nice To Haves

Hands-on experience with DEL data.
Drug discovery experience, especially in protein-ligand modeling or molecular optimization contexts.
Experience with Boltz, AlphaFold or AlphaFold-derived methods, equivariant GNNs, diffusion models, protein language models, or molecular encoders.
Experience training or extending cofolding, protein-ligand, protein-protein, structure prediction, diffusion, or geometric deep learning models.
Experience with distributed model training and large-scale scientific data pipelines.
Familiarity with active learning or closed-loop molecular design.
Experience integrating ML models into agentic scientific workflows.

Responsibilities

Train and evaluate cofolding models for protein-ligand and related molecular discovery applications.
Use contrastive learning, representation learning, self-supervised learning, or related methods where they help improve cofolding models trained on molecules, proteins, structures, and experimental readouts.
Develop modeling approaches that make DEL data more useful for learning binding, enrichment, selectivity, and structure-activity signals.
Build and evaluate models informed by Boltz, AlphaFold-style cofolding, equivariant GNNs, and related structure-aware ML methods.
Design training objectives, including contrastive, self-supervised, or multimodal objectives, that connect ligands, proteins, structures, assays, simulations, and experimental data.
Build rigorous evaluation frameworks that distinguish meaningful molecular learning from dataset artifacts, leakage, or spurious correlations.
Collaborate with data and platform teams to define datasets, labels, negatives, controls, and metadata needed for model training.
Partner with computational chemistry and biophysics teams to connect model outputs to physically and chemically meaningful hypotheses.
Work with low-data learning scientists to identify which DEL, assay, simulation, or structural data would most improve model performance in focused chemical spaces.
Work with research engineers to scale training, inference, and evaluation workflows.
Help expose trained models and model-derived capabilities as tools for scientists and AI agents.