Overview In this role you will advance AI-enabled drug discovery at Takeda by developing agentic AI systems and orchestrating multi-step computational workflows. You will integrate chemical and biological databases with foundation models and scientific software to accelerate the DMTA cycle. You will lead strategic initiatives and deploy predictive tools across the design process, working with cross-functional teams to deliver scalable, data-driven solutions. This is a hands-on, impact-driven opportunity in Boston to shape early-stage discovery pipelines.
Compensation / Benefits- medical insurance
- dental insurance
- vision insurance
- 401(k) with company match
- tuition reimbursement
- paid volunteer time off
Responsibilities- Develop and apply agentic AI systems in drug discovery
- Integrate chemical/biological databases, foundation models, and scientific tools into multi-step workflows
- Lead strategic initiatives to accelerate the DMTA cycle
- Deploy predictive tools across the design process
- Build and maintain scalable computational workflows and pipelines
- Collaborate with cross-functional teams to translate AI/chemoinformatics into practice
Key requirements- PhD with 2+ years in pharma/biotech
- MLOps and model lifecycle management experience (workflow orchestration, CI/CD, model registries, monitoring, versioning, deployment)
- Experience building and querying ultra-large chemical databases with scalable data engineering and HPC/cloud environments
- Strong programming/scripting in Python, R, C/C++
- RDKit or equivalent cheminformatics toolkit expertise
- Comprehensive DMTA cycle knowledge and track record deploying tools across design processes
- Experience leading strategic DMTA acceleration initiatives
- cross-functional collaboration
- strategic thinking
- impact-focused communication
- MLOps
- workflow orchestration
- CI/CD
