Research Scientist, AI/ML Biologics - Methods Development - Method

By clicking the “Apply” button, I understand that my employment application process with Takeda will commence and that the information I provide in my application will be processed in line with Takeda’s Privacy Notice and Terms of Use. I further attest that all information I submit in my employment application is true to the best of my knowledge.

Job Description

At Takeda, we are a forward-looking, world-class R&D organization that unlocks innovation and delivers transformative therapies to patients. By focusing R&D efforts on three therapeutic areas and other targeted investments, we push the boundaries of what is possible to bring life‑changing therapies to patients worldwide.

The AI/ML organization at Takeda is building a team to transform how medicines are discovered. Our goal is to apply AI and machine learning across the entire drug discovery process, not just isolated steps, but as an integrated approach from target identification through development. This requires discernment: knowing which models and methods fit each problem, and the creativity to adapt when they don't. We work with foundational models, generative approaches, and autonomous systems, but the tools only matter when paired with people who understand the science deeply enough to use them well. Our team brings together computational scientists, biologists, engineers, and drug hunters. If you want to contribute your expertise to hard problems alongside colleagues with different perspectives and help shape how AI delivers real impact in drug discovery, we’d like to hear from you.

Objective / Purpose

We are seeking a skilled and motivated Scientist to join our Large Molecule AI/ML team within Computational Sciences. This role focuses on developing and applying machine learning methods to accelerate antibody discovery and optimization on active pipeline projects. You will work closely with protein engineers, computational scientists, and experimental teams to deliver predictive models that directly impact candidate selection and developability assessment. The ideal candidate combines strong ML fundamentals with an interest in biologics and thrives in a fast‑paced, collaborative R&D environment.

Accountabilities Develop and implement machine learning models for antibody property prediction, including developability attributes (stability, aggregation, immunogenicity, viscosity) to support active discovery programs. Build predictive tools that rank antibody candidates, flag potential liabilities, and suggest sequence modifications for improved properties. Benchmark and evaluate external computational methods and commercial AI platforms; recommend best‑in‑class tools for integration into internal workflows. Innovate, develop, and apply predictive models for protein design and developability engineering, utilizing large‑scale NGS, in vitro, in vivo and other proprietary in‑house and external data sources. Investigate transfer learning and few‑shot learning approaches to enable rapid model deployment on new antibody formats (multi‑specifics, VHH, ADCs) with limited training data. Collaborate with experimental teams to validate predictions against assay data, iterate on model development, and integrate AI/ML outputs into Design‑Predict‑Make‑Confirm cycles. Establish and maintain AI performance dashboards and KPIs to track prediction accuracy, model reliability, and impact on project timelines. Stay current with advances in machine learning for protein science and contribute to internal knowledge sharing. Education & Competencies (Technical and Behavioral) Required PhD in Computational Biology, Bioinformatics, Computer Science, or related field, OR MS with 6+ years relevant experience, OR BS with 10+ years relevant experience. Proven track record in developing machine learning models for biological or chemical data. Proficiency in Python and machine learning frameworks (PyTorch, TensorFlow, or scikit‑learn). Experience with protein sequence analysis and understanding of antibody structure‑function relationships. Strong analytical and problem‑solving skills with demonstrated ability to work both independently and collaboratively. Excellent communication skills to convey complex computational concepts to diverse scientific audiences. Preferred Experience with protein language models (ESM, ProtTrans) or other deep learning architectures for protein property prediction. Familiarity with antibody developability assessment (stability, aggregation, immunogenicity). Experience with transfer learning or active learning approaches. Prior experience in pharmaceutical or biotech R&D environment. Experience with cloud computing (AWS, GCP) and version‑controlled ML pipelines. Additional Competencies Common in Strong Candidates Ability to lead cross‑functional initiatives and mentor junior scientists. Experience in translating computational insights into experimental strategies Strong publication record or demonstrated thought leadership in AI for biology and