Research Scientist, Molecular AI

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.

About the role

You will 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. This role involves collaboration with multidisciplinary teams to integrate validated models into production-ready drug discovery workflows and apply computational methods to structural and sequence datasets.

Responsibilities

• Develop and iterate on deep learning models across the molecular modeling stack (e.g., structure prediction, protein–ligand co-folding, affinity, generative design).
• Design and execute rigorous benchmarking and evaluation pipelines that connect offline metrics to real-world performance.
• 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 for 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.

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 in designing controlled experiments, interpreting results critically, and iterating effectively on model development.
• Strong written and verbal communication skills, and the ability to collaborate in a fast-paced, multidisciplinary research environment.

Preferred Qualifications

• 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.

Pay

For Location: Boston, MA, the U.S. base salary range is $116,000.00 - $182,270.00. The actual base salary offered may depend on factors such as qualifications, relevant experience, specific skills, education, and location.

Benefits

• Eligibility for short-term and/or long-term incentives.
• Medical, dental, and vision insurance.
• 401(k) plan with company match.
• Short-term and long-term disability coverage.
• Basic life insurance.
• Tuition reimbursement program.
• Paid volunteer time off.
• Company holidays.
• Well-being benefits.
• Up to 80 hours of sick time per calendar year.
• New hires eligible to accrue up to 120 hours of paid vacation.

Schedule

Full time, exempt position.