Research Scientist, Molecular AI

3316 Takeda Development Center Americas•Boston, MA

2d•Onsite

About The Position

We are seeking a Research Scientist to help shape the future of AI-enabled drug discovery at Takeda, with a focus on structure-guided small-molecule design. Working across AI/ML, structural biology, and medicinal chemistry, you will develop cutting-edge computational approaches to explore chemical space more effectively and translate scientific advances into life-saving therapeutic impact.

Requirements

Ph.D. in Computational Biology, Biophysics, Computer Science, Computational Chemistry, or a related field, with a research focus in ML for molecular modeling (e.g., structure prediction, co-folding, affinity, or molecular design).
Hands-on experience developing, training, and validating deep learning models, including architectures relevant to structural biology and chemistry (e.g., transformers, equivariant neural networks, diffusion models).
Direct experience with modern structure prediction or co-folding methods (e.g., AlphaFold2/3, RoseTTAFold, Chai-1, Boltz) or comparable molecular ML systems.
Strong proficiency in Python and modern ML frameworks (PyTorch and/or JAX).
Demonstrated scientific rigor: the ability to design controlled experiments, interpret results critically, and iterate effectively on model development.
Strong written and verbal communication skills, and the ability to collaborate in a fast-paced, multidisciplinary research environment.

Nice To Haves

Postdoctoral or industry experience in structure prediction, structure-based drug design, or a related computational domain.
Familiarity with binding affinity prediction, including structure-based or physics-informed approaches.
Authorship of publications or preprints in relevant venues (e.g., NeurIPS, ICML, ICLR).
Experience deploying ML workflows on public cloud infrastructure (GCP, AWS, or Azure) and/or GPU/HPC environments.
Familiarity with agentic coding tools (e.g., Claude Code, Codex) to accelerate research prototyping.

Responsibilities

Develop and iterate on deep learning models across the molecular modeling stack — structure prediction, protein–ligand co-folding, affinity, and/or generative design — building on the latest research from the field.
Design and execute rigorous benchmarking and evaluation pipelines that connect offline metrics to real-world performance and hold models to a high scientific bar.
Partner with senior scientists and engineers to integrate validated models into production-ready drug discovery workflows.
Apply computational and data-analysis methods to structural and sequence datasets to generate insights that guide model development.
Apply generative AI and predictive ML models to design and prioritize chemical matter for research projects.
Communicate findings through internal scientific talks, technical write-ups, and contributions to peer-reviewed publications.
Collaborate across multidisciplinary teams — ML engineers, structural biologists, and software engineers — to prototype and scale impactful solutions.