CADD Scientist​/Senior CADD Scientist

Chemify is revolutionising chemistry. We are creating a future where the synthesis of previously unimaginable molecules, drugs, and materials is instantly accessible. By combining AI, robotics, and the world's largest continually expanding database of chemical programs, we are accelerating chemical discovery to improve quality of life and extend the reach of humanity.

Our Chemifarm facility in Glasgow operates a growing fleet of advanced robotic systems that automate synthesis, optimisation, and library generation. This gives our computational scientists something rare: a direct, high‑throughput bridge from in silico design to physically synthesised molecules, closing the design–make–test loop at a pace conventional drug discovery organisations cannot match.

San Francisco (hybrid) or fully remote from Boston / San Diego.

Regular travel to our Glasgow HQ / Chemifarm.

We are seeking a CADD Scientist to drive computer‑aided drug design on Chemify's commercial programmes and computational platform. You will sit within a cross‑disciplinary team — computational chemists, in‑house and partner medicinal chemists, AI researchers, data engineers, and automation scientists — and help translate structure, simulation, and machine learning into molecules we actually make.

What sets this role apart is the design–make–test loop: working directly with partner chemists on medicinal‑chemistry strategy, you will design and prioritise molecules for synthesis and see them physically made on our robotic platform within days rather than months.

If you are energised by solving complex problems at the intersection of chemistry, physics, and AI — and by seeing your designs synthesised and tested in days — we’d love to welcome you to our team.

• Run computational design across the CADD stack — docking, pharmacophore, shape and 3D‑similarity, MD, FEP, and QSAR — choosing appropriate physics‑ and ML‑based approaches for each question.
• Design, enumerate, and prioritise molecules and libraries for synthesis, and triage and analyse the results across DMTL cycles.
• Work with in‑house and partner chemists on MPO, translating SAR and diverse assay readouts into actionable, biologically relevant design hypotheses.
• Communicate computational reasoning, trade‑offs, and recommendations clearly to working chemists and project leads.
• Apply modern deep learning for molecular design (GNNs, generative models, property prediction) where it complements traditional CADD methods.
• Contribute to product ionising CADD methods into a reproducible, API‑first toolkit; partner with Infrastructure on cost‑effective GPU/HPC workflows.
• Own the computational design strategy on assigned programmes from hit discovery through lead optimisation; mentor junior CADD scientists, partner with the Head of Advanced Machine Learning on growth, and act as the scientific interface with customers.

You are a credible computational chemist who is equally comfortable reasoning about protein–ligand interactions and shipping code that runs in production. You care about getting real molecules made, not only writing elegant methods.

• PhD (or equivalent experience) in Computational Chemistry, Structural Biology, Biophysics, Physics, or a closely related field — with 2+ years (CADD Scientist) or 5+ years (Senior) of hands‑on CADD experience in small‑molecule drug discovery.
• Grounding in both structure‑ and ligand‑based drug design — protein–ligand biophysics on one side, and pharmacophore, shape, and SAR‑driven design on the other — with hands‑on use of the standard CADD stack (e.g. MOE, PyMOL, OpenMM / GROMACS / AMBER).
• Familiarity with core drug discovery and medicinal chemistry principles, and the ability to translate diverse assay readouts into biologically relevant design hypotheses.
• Strong Python and at least one core cheminformatics toolkit (e.g. RDKit, Open Eye); real experience inside the drug‑discovery loop (SAR, MPO, DMTL cycles, library enumeration); comfort with GPU‑accelerated simulation and cloud/HPC workflows.
• Working knowledge of modern deep learning for molecular design (GNNs, generative models,…