Research Scientist AI/ML Foundational Models

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. Position Overview We are seeking Scientists to develop and deploy foundational AI models that will transform drug discovery across Takeda. As part of the AI/ML Foundation team, you will build large‑scale models including large language models (LLMs), diffusion models, and multimodal architectures that integrate diverse data types—omics, biomedical imaging, protein 3D structures, and molecular representations. This role requires deep expertise in modern deep learning architectures combined with foundational knowledge of biology, chemistry, and disease biology to ensure models are scientifically grounded and impactful. Accountabilities Develop and train foundational AI models (LLMs, diffusion models, flow‑matching architectures) for drug discovery applications, with capability to pre‑train on large‑scale scientific corpora and molecular datasets. Fine‑tune and adapt pre‑trained foundation models (protein language models, chemical LLMs, vision transformers) for Takeda‑specific applications in target identification, disease modeling, and molecular design and discovery. Build multimodal foundation models integrating diverse data types including omics (genomics, transcriptomics, proteomics), biomedical imaging, protein 3D structures, and molecular representations. Apply and extend state‑of‑the‑art approaches including graph neural networks, transformer‑based protein language models, and multimodal learning frameworks. Apply domain expertise in biology, chemistry, and/or disease biology to guide model architecture decisions, training data curation, and evaluation strategies ensuring scientific validity. Implement state‑of‑the‑art generative architectures (diffusion, score‑based models, autoregressive transformers) for molecular generation, protein design, and multi‑objective optimization. Collaborate with computational scientists across domains to deploy foundation models that address diverse discovery needs across small molecules, biologics, and emerging modalities. Stay current with advances in foundation models, generative AI, and multimodal learning; contribute to internal knowledge sharing and external publications. Education & Requirements PhD in Computer Science, Machine Learning, Computational Biology, Bioinformatics, or related field or MS with 6+ years relevant experience, or BS with 8+ years relevant experience. Deep expertise in modern deep learning architectures including transformers, diffusion models, and/or generative models. Strong experience training large‑scale models with proficiency in PyTorch and distributed training frameworks. Foundational knowledge of biology, chemistry, or disease biology sufficient to guide scientifically meaningful model development. Experience with at least one of: protein language models (ESM, ProtTrans), molecular generative models, or biomedical vision models. Experience with cloud computing (AWS, GCP) and GPU cluster training at scale. Preferred Experience building or fine‑tuning foundation models in pharmaceutical or life sciences settings. Expertise in multimodal learning integrating text, images, and structured molecular data. Experience with omics data analysis (genomics, transcriptomics, proteomics) and knowledge graph. Familiarity with protein structure prediction and 3D molecular representations. Publications in top‑tier ML venues (NeurIPS, ICML, ICLR) or computational biology journals. Experience with model compression, efficient inference, or production deployment of large models. Strong background in large‑scale data integration and multimodal modeling for biological systems. Proficiency in Python and ML libraries (PyTorch, TensorFlow, scikit‑learn); familiarity with Unix tools. Excellent collaboration and communication skills. Additional Information The position will be based in Cambridge, MA. Takeda Compensation and Benefits Summary We understand compensation is an important factor as you consider the next step in your career. We are committed to equitable pay for all employees, and we strive to be more transparent with our pay practices. Location Boston, MA U.S. Base Salary Range $111,800.00 - $175,670.00 The estimated salary range reflects an anticipated range for this position. The actual base salary offered may depend on a variety of factors, including the qualifications of the individual applicant for the position, years of relevant experience, specific and unique skills, level of education attained, certifications or other professional licenses held, and the location in which the applicant lives and/or from which they will be performing the job. The actual base salary offered will be in accordance with state or local minimum wage requirements for the job location. U.S. based employees may be eligible for short‑term and/or long‑term incentives. U.S. based employees may be eligible to participate in medical, dental, vision insurance, a 401(k) plan and company match, short‑term and long‑term disability coverage, basic life insurance, a tuition reimbursement program, paid volunteer time off, company holidays, and well‑being benefits, among others. U.S. based employees are also eligible to receive, per calendar year, up to 80 hours of sick time, and new hires are eligible to accrue up to 120 hours of paid vacation. EEO Statement Takeda is proud in its commitment to creating a diverse workforce and providing equal employment opportunities to all employees and applicants for employment without regard to race, color, religion, sex, sexual orientation, gender identity, gender expression, parental status, national origin, age, disability, citizenship status, genetic information or characteristics, marital status, status as a Vietnam era veteran, special disabled veteran, or other protected veteran in accordance with applicable federal, state and local laws, and any other characteristic protected by law. Worker Type Employee Worker Sub‑Type Regular Time Type Full time Job Exempt Yes It is unlawful in Massachusetts to require or administer a lie detector test as a condition of employment or continued employment. An employer who violates this law shall be subject to criminal penalties and civil liability. #J-18808-Ljbffr