Basel, Basel, Switzerland
Passionate about using AI and software engineering to transform how we design and synthesize molecules — innovating for safer, more efficacious active ingredients.
I work on digitalizing medicinal chemistry. I envisioned and spearheaded the development of a company-wide computational platform that supports chemists in generating robust, AI-ready experimental data. This data foundation enables innovation in how we work, shifting from reaction-level data to whole synthetic routes, opening the way for deep integration with computer-aided synthesis tools. These tools leverage internal, external, and legacy ELN data to predict the most promising experiments, accelerating synthesis cycles, improving effectiveness, and reducing waste. The successful implementation is the outcome of close scientific partnerships with leading external teams at IBM and MIT, and deep collaboration across internal and external contributors to deliver an evolving solution. My focus: scouting emerging technologies, prototyping AI solutions, and preparing the next leap — agentic, automation-driven decision-making to empower scientists to achieve breakthrough science.
I worked on breaking the active ingredient design paradigm by introducing inverse design into our medicinal chemistry organization. I scouted and evaluated technologies to accelerate active ingredient design, improving the effectiveness of the Design–Synthesis–Test–Analysis (DSTA) cycle. I explored early solutions in generative chemistry to enable multi-objective, property-driven design. My work included technology scouting, prototyping, and disseminating insights across teams to drive adoption and collaboration.
As Group Leader, I managed and developed a computational chemistry team, fostering collaboration, growth, and delivery excellence. I coordinated cross-functional projects and, as part of the leadership team, contributed to the definition and execution of strategic decisions for the R&D organization. In parallel, I investigated the Design–Synthesis–Test–Analysis (DSTA) cycle to identify opportunities to improve efficiency and effectiveness. I championed the adoption of modern computational tools to streamline workflows, enhance decision-making, and accelerate active ingredient discovery.
Topics: computational biophysics, homology modeling, computer aided drug design Project: molecular assemblies • Assessed growth regulation of the Yersinia injectisome (T3SS) • Outlined the expression regulatory mechanism of M. Tubercolosis T7SS • Devised new techniques to probe protein-protein and protein-DNA interactions (transcription factors, TAL, nucleases) • Devised new methods to quantify protein-ligand interactions (drug design) • Individuated the key interaction between bacterial LPS and human MD-2/TLR4 receptor
Project: Computational investigation of organic and bioorganic catalysts • Designed and implemented new methods for the study of enzymatic catalysis • Implemented new computational methods to study behavior of chromophores (retinal, phytochrome)
Visiting PhD student in the group of Prof. Jeremy Harvey Project: Computational investigation of the racemization process in chiral iron complexes
Project: DFT approaches to the study of reaction mechanisms in organic chemistry • Studied the electrochemical properties of drug candidates (ADMET properties)