Senior Research Scientist: Insilico Prediction Platform Lead

Role Summary

Senior Research Scientist: Insilico Prediction Platform Lead who will drive the strategy, development, and integration of automation, AI, and ML–powered prediction models to accelerate early-stage drug discovery across Elanco’s research portfolio. The role shapes the platform vision, partners with scientific and technical teams, and enables computational approaches for both small and large molecule innovation. This position builds scalable, data-driven, and automated research capabilities within pharmaceutical R&D.

Responsibilities

• Develop and execute the technical strategy for Elanco’s structural and property prediction platform in alignment with key scientific and therapeutic priorities.
• Evaluate, select, and implement advanced AI/ML models—including generative, diffusion-based, deep learning, and graph-based approaches—to support small and large molecule discovery.
• Lead the integration of new computational and automation capabilities into existing discovery workflows and research pipelines.
• Establish standards and best practices for model ingestion, benchmarking, validation, deployment, reproducibility, and scientific data integrity.
• Build scalable workflows and automated processes that streamline predictive modeling and improve scientific throughput.
• Continuously evolve the platform by incorporating stakeholder feedback, monitoring performance indicators, and tracking scientific and technological advancements.

Qualifications

• Required: Education — Bachelor’s, Master’s, or PhD in molecular biology, biotechnology, bioengineering, bioinformatics, cheminformatics, computational biology, data science, or a related scientific discipline.
• Required: Experience — 8+ years in computational drug discovery, including at least 5 years leading AI/ML or automation-focused projects or platforms within pharmaceutical or biotech R&D.
• Required: Demonstrated success developing, applying, and deploying advanced computational and automated workflows that accelerate drug discovery, with meaningful impact in large molecule programs.
• Required: Ability to translate complex computational concepts into clear, actionable insights for multidisciplinary scientific and business partners.
• Preferred: Scientific domain-first backgrounds; technical candidates with strong scientific grounding are prioritized.
• Preferred: Expertise developing, benchmarking, automating, and deploying state-of-the-art AI/ML models, including deep learning, generative models, diffusion models, GNNs, and transformer-based architectures.
• Preferred: Strong scientific programming experience (Python, R, or C++) and productionizing cheminformatics/bioinformatics workflows with tools such as RDKit, TensorFlow, PyTorch, Benchling, AlphaFold, Protein LLMs, Schrödinger, Chai, Boltz; Git-based CI/CD and reproducibility frameworks.
• Preferred: Deep understanding of the drug discovery pipeline (ADME/Tox, PK/PD modeling, SAR/QSAR, data analysis, protein engineering, molecular modeling, dynamics, and structure-based design). Experience in animal health is a plus.
• Preferred: Proven leadership and communication skills with a track record of influencing interdisciplinary teams and presenting complex modeling concepts to diverse audiences.
• Preferred: Hands-on experience building scalable or cloud-based computational and automation platforms supporting virtual screening, high-throughput modeling, large-scale data analysis, and ML model training.

Education

• Bachelor’s, Master’s, or PhD in molecular biology, biotechnology, bioengineering, bioinformatics, cheminformatics, computational biology, data science, or a related scientific discipline.