Research Senior Scientist, Cheminformatics AI/ML

Takeda•Boston, MA

76d•$137,000 - $215,270•Onsite

About The Position

We are seeking a skilled cheminformatic scientist to join Takeda’s cheminformatics team. This role will be key to fostering a “prediction-first” culture, integrating cheminformatics, computational chemistry, and machine learning to accelerate drug design. The candidate will collaborate closely with global teams in medicinal chemistry, DMPK, and AI/ML, defining a roadmap for computational tools that empower medicinal chemists to drive innovation.

Requirements

PhD in Computational Chemistry, Cheminformatics, Computer Science or related disciplines, with 2+ years of experience in pharmaceutical or biotech setting.
Demonstrated experience developing and applying agentic AI systems in drug discovery, including integrating and orchestrating chemical and biological databases, foundation models, scientific software tools, and multi-step computational workflows.
Hands-on experience with MLOps and model lifecycle management, including workflow orchestration, CI/CD, model registries, monitoring, version control, and deployment in cloud or high-performance computing environments.
Experience building, maintaining, and searching ultra-large chemical databases using scalable data engineering, distributed computing, and high-performance search technologies; familiarity with cloud storage, vector search, and chemical indexing is highly desirable.
Solid programming and scripting capabilities (e.g., Python, R, C/C++) with a proven ability to design and automate scalable computational workflows.
Strong expertise in cheminformatics toolkits such as RDKit. Comprehensive knowledge of the DMTA cycle with demonstrated success in deploying predictive tools across the design process. Experience leading strategic initiatives to accelerate DMTA cycle.

Nice To Haves

Familiarity with cloud storage, vector search, and chemical indexing is highly desirable.

Responsibilities

Develop and apply agentic AI solutions for drug discovery, including autonomous or human-in-the-loop workflows that integrate scientific reasoning, molecular design, data analysis, and computational tools.
Identify opportunities throughout the DMTA cycle where predictive tools can drive acceleration. Build predictive models for molecule design and optimization. Extract medchem design knowledge from large-scale chemical and biological datasets.
Establish and maintain MLOps capabilities for predictive models, including reproducible training and deployment pipelines, model lifecycle orchestration, performance monitoring, versioning, and scheduled retraining.
Build, maintain, and enable efficient search and analytics across ultra-large chemical databases, including scalable data ingestion, standardization, indexing, similarity and substructure search, and distributed computing workflows.
Stay updated with emerging trends in computational chemistry and machine learning as applied to drug discovery. Implement and execute innovative computational methodologies and tools such as AI-based drug discovery, generative chemistry, synthesizable chemical space exploration, DNA Encoded Library (DEL) data analysis and DEL/ML application.
Serve as a trusted thought partner, helping to drive ideation and execution of innovative chemistry strategies that meet Takeda’s therapeutic goals.