Scindo is building the next generation of enzyme-powered chemistry, combining wet-lab data with state-of-the-art machine learning. We are looking for a Machine Learning Scientist to design and deploy models that push the boundaries of enzyme prediction, reaction modelling, and generative catalyst design.

Essential requirements

• PhD (or equivalent) in Physics, Applied Mathematics, Computational Chemistry, or related field.
• Proven experience applying machine learning to molecular systems, e.g. protein engineering, enzyme catalysis, reaction prediction, molecular de novo design, molecular dynamics.
• Strong background working with deep learning architectures relevant to molecules/sequences:

-Transformers (e.g. ProtBERT, ESM, AlphaFold-like)

-Equivariant neural networks / GNNs (SchNet, DimeNet, SE(3)-Transformers)

-Generative models (diffusion, VAEs, autoregressive) for proteins, molecules or materials.

• Hands-on experience with molecular dynamics and simulation data; familiarity with force fields, ab initio methods, or enhanced sampling.
• Excellent mathematics foundation: linear algebra, optimisation, probability, statistical mechanics, PDE/ODE modelling.
• Strong programming in Python (PyTorch/TensorFlow, JAX, NumPy/SciPy); experience with scientific libraries such as RDKit, ASE, DeepChem.

Desirable skills

• Experience with MLOps and end-to-end large-scale model development. (e.g. training, evaluation, benchmarking and deployment)
• Familiarity with vector databases and embeddings (Qdrant, Milvus, FAISS) for chemical/sequence similarity search.
• HPC/GPU cluster experience, performance optimisation, distributed training.
• Background in spectroscopy (IR/UV/Vis/NMR) and/or computational thermodynamics/kinetics.
• Exposure to enzyme engineering, biocatalysis, or structural biology data.

What we offer

• Opportunity to build a machine learning stack from the ground up, with direct impact on real-world sustainable chemistry.
• A highly collaborative lab–computational environment: every model prediction is tested in-house, feeding back into data pipelines.
• Central London lab/office with a fast-growing interdisciplinary team.