Senior Director, AIRx Computational Chemistry

Takeda Research is constructing a Lab of Tomorrow built on AI, automation, new ways of working, and talent with the singular vision of delivering differentiated medicines to the clinic at speed and cost. To catalyze these efforts, Takeda is creating two complementary units: AI Research Accelerator (AIRx) and Lab Automation & Transformation (LAT). 

AIRxwill consist of a dedicated group of experienced drug hunters with the autonomy of a biotech and the resources of a leading pharmaceutical company. It is designed to incubate the future AI-powered operating models and deliver candidates to the clinic at industry leading speed and success rates.

Purpose 

Reporting to the Head of AIRx, the AIRx Computational Chemist sits at the scientific heart of AIRx's AI-first operating model. This role drives in silico molecular design, leverages predictive models, and applies generative chemistry to power rapid DMTA cycles — directly enabling the speed and precision that define the AIRx incubator In AIRx, computational chemistry is a first-order decision-making function — generative proposals from this role directly shape what gets synthesized, what gets deprioritized, and ultimately what reaches the clinic. The role is deeply hands-on, with a unique opportunity to directly shape candidates that advance to the clinic through close collaboration with the wider AIRx design team. 

Accountabilities 

• Apply generative AI, structure-based design, free energy perturbation, and predictive ML models to design and prioritize chemical matter 

• Partner closely with Medicinal Chemists to translate computational outputs into actionable synthesis priorities; challenge and be challenged in equal measure 

• Lead and oversee virtual screening campaigns, ADMET predictions, and selectivity assessments to inform and accelerate design decisions 

• Contribute to building and refining AI/ML model training datasets from AIRx experimental outputs 

• Develop and maintain computational workflows that increase team speed and reproducibility 

• Interpret and integrate structural biology data (X-ray, cryo-EM) into computational design strategies 

• Communicate complex computational findings clearly to cross-disciplinary colleagues and governance forums 

• Stay current with advances in generative AI, protein structure prediction, and ML methods; proactively apply new approaches 

Qualifications & Competencies 

• PhD in computational chemistry, cheminformatics, biophysics, or closely related discipline 

• 12–15+ years of drug discovery experience with demonstrated track record of computational impact on programs 

• Proficiency across computational tools: molecular docking, MD simulation, FEP, QSAR/ADMET modeling 

• Strong coding skills (Python required); experience building and deploying ML models in a drug discovery context 

• Experience with structure-based drug design; ability to interpret crystallography or cryo-EM data 

• Experience applying generative AI or large language models to molecular design preferred 

• Collaborative, communicative, and comfortable at the wet/dry scientific interface 

ADDITIONAL INFORMATION

• The position will be based in Cambridge, MA.  This position is currently classified as “hybrid” by Takeda’s Hybrid and Remote Work policy