AI-driven drug discovery platform combining physics simulations with generative models
AQEMIA applies physics-based ML to drug discovery, moving beyond traditional screening and experimental dependency. The tech stack is lean but production-grade—Python, Kubernetes, ArgoCD, Terraform—reflecting a computational-first, DevOps-mature organization. Active pain points (scaling scientific teams, integrating physics simulations, accelerating discovery timelines) and a research-heavy hiring mix (5 research roles, 1 data, 2 engineers) signal a company pivoting from proof-of-concept toward operational scale: lead programs in in vivo optimization, a focus on program governance, and deliberate effort to double active programs and the program-management team.
Notable leadership hires: Program Lead
AQEMIA is a drug-discovery platform company founded in 2019, based in Paris with a London office, operating across France and the UK. The platform combines quantum-inspired physics calculations with generative AI to design novel drug candidates without reliance on large experimental datasets—a computational alternative to traditional high-throughput screening. The company operates its own proprietary programs (with lead candidates in in vivo optimization) and collaborates with pharmaceutical partners. The portfolio includes work on oncology and other major disease areas. The organization is 51–200 people, recently added to the French Tech 120 cohort and active in both the BioIndustry Association and Knowledge Quarter networks.
Python, Docker, Kubernetes, ArgoCD, AWS, Terraform, and GitHub Actions—core infrastructure for computational chemistry and ML model deployment.
Lead program optimization, structure-based generative AI models, physics-based simulation integration into ML workflows, virtual screening, hit generation, and in vivo optimization. Also scaling program governance and management infrastructure.
Other companies in the same industry, closest in size