ML Scientist: Data-Efficient Drug Discovery

Lilasciences; Greater London; Presencial; GBP 171 000 - 269 000; Tempo integral

Vantagens oferecidas por esta oferta de emprego

Equity

Full benefits package (US) including:

Medical, dental, and vision coverage

Life and disability insurance

Flexible time off

Paid parental leave

Educational assistance program

Commuter benefits

Bike share memberships

Lunch program

International Benefits

Resumo da oferta

Lila Sciences is seeking a Machine Learning Scientist, Data-Efficient Learning for Drug Discovery to build models that learn from scarce, high-quality data and guide data acquisition decisions.

You'll develop active learning, meta-learning, and uncertainty-aware approaches to operate in tightly focused chemical spaces, integrating multimodal data and collaborating across experimental and computational teams to accelerate discovery.

Qualificações

• PhD or equivalent in ML, computational chemistry, computational biology, statistics, CS, bioengineering, or related field.
• Strong experience training ML models in low-data regimes.
• Experience with active learning, Bayesian optimization, experimental design, meta-learning, fine-tuning, transfer learning, uncertainty estimation, or related data-efficient learning methods.
• Experience building ML models for scientific, molecular, biological, chemical, pharmacological, biochemical, or other high-dimensional experimental datasets.
• Experience with multimodal learning or methods that combine heterogeneous data sources.
• Ability to reason about data acquisition strategy, not only model fitting.
• Strong scientific judgment and ability to connect model behavior to experimental decisions.
• Practical experience with PyTorch, JAX, scikit-learn, or equivalent ML tools.
• Ability to collaborate across ML, data, computational science, experimental, and drug discovery teams.

Responsabilidades

• Build ML models that perform well in low-data regimes for drug discovery and molecular optimization.
• Design data acquisition strategies that identify which compounds, assays, DEL selections, simulations, structural predictions, or experiments should be run next to maximize learning.
• Develop active learning, meta-learning, fine-tuning, transfer learning, and uncertainty-aware modeling approaches for focused chemical spaces.
• Train models on low-quantity, high-quality datasets generated by Lila's experimental, computational, and agentic discovery systems.
• Build multimodal models that can integrate DEL data, simulation outputs, assay data, protein and structural information, chemical features, literature or text-derived signals, images, and experimental metadata.
• Partner with experimental, computational, and drug discovery teams to ensure data acquisition plans are scientifically meaningful and operationally feasible.
• Evaluate models through learning curves, prospective validation, retrospective benchmarks, uncertainty calibration, and decision-focused metrics.
• Develop closed-loop learning workflows that continuously update models as new data arrives from experiments, simulations, and automated systems.
• Translate model predictions and uncertainty into practical recommendations for compound selection, assay selection, batch design, or next experiments.
• Work with platform and agent teams to expose model-driven recommendations as tools for scientists and AI agents.

Conhecimentos

Low-data ML

Active learning

Bayesian optimization

Meta-learning

Fine-tuning

Transfer learning

Uncertainty estimation

Multimodal learning

Model evaluation

Formação académica

PhD or equivalent experience

Ferramentas

PyTorch

JAX

scikit-learn

Descrição da oferta de emprego

Lila Sciences is seeking a Machine Learning Scientist, Data-Efficient Learning for Drug Discovery to build models that learn from scarce, high-quality data and guide data acquisition decisions.

You'll develop active learning, meta-learning, and uncertainty-aware approaches to operate in tightly focused chemical spaces, integrating multimodal data and collaborating across experimental and computational teams to accelerate discovery.