Advisor – Scientific Machine Learning Scientist – Drug Delivery Device Development Full-time

Advisor – Scientific Machine Learning Scientist

At Lilly, we unite caring with discovery to make life better for people around the world. We are a global healthcare leader headquartered in Indianapolis, Indiana. Our employees around the world work to discover and bring life-changing medicines to those who need them, improve the understanding and management of disease, and give back to our communities through philanthropy and volunteerism. We give our best effort to our work, and we put people first. We're looking for people who are determined to make life better for people around the world.

Delivery, Devices, and Connected Solutions (DDCS) sits within Eli Lilly's Product Research & Development organization. We are a diverse team of scientists and engineers responsible for discovering, designing, and developing patient-centric drug delivery solutions across a broad range of modalities — from injection devices to novel routes of administration and nanomedicines. DDCS drives the drug delivery innovation agenda across early and late development to meet the needs of an expanding portfolio that spans small molecules, biologics, and nucleic acid therapeutics.

DDCS is organized around a matrix model with strong disciplinary and functional horizontals supporting innovation and commercialization verticals. Our vision is to get our medicines to more patients faster by accelerating reach and scale, guided by three strategic pillars: Delivery Systems, Robust & Sustainable, and Patient Experience + Outcomes.

The Modeling & Simulation team within DDCS advances predictive modeling capabilities across molecular-to-system scales and single-to-multi-physics domains, integrating scientific machine learning (SciML) and AI to accelerate design, de-risk development, and deepen mechanistic understanding for drug delivery systems.

We are seeking an innovative Advisor – Scientific Machine Learning Scientist to join the Modeling & Simulation team. This role uniquely combines deep domain expertise in physics and engineering with cutting-edge machine learning techniques to solve complex scientific problems that traditional approaches cannot address. You will develop physics-informed neural networks, hybrid models, and multi-scale modeling solutions that accelerate device innovation, optimize formulations, and enhance patient outcomes — while communicating insights to senior leadership to drive strategic decisions.

This is a hands-on technical role that combines model development, capability building, and cross-functional collaboration to inform decisions from molecular interactions and material behavior to fluid/solid mechanics, device performance, and patient-use conditions.

Responsibilities:

• Design & Build Physics-Informed Models: Develop physics-informed neural networks, operator learning architectures, and hybrid modeling approaches that combine mechanistic/first-principles models with data-driven ML components to capture complex phenomena in device performance, drug release kinetics, and patient interactions.
• Multi-Scale & Multi-Physics Integration: Build models that integrate information from molecular to device to patient levels, incorporating temporal dynamics and heterogeneous data sources; create surrogate models that efficiently approximate expensive computational simulations to enable rapid design space exploration.
• Uncertainty Quantification & Decision Support: Implement Bayesian approaches, ensemble techniques, Gaussian processes, and active learning to provide confidence bounds critical for medical device safety decisions and regulatory submissions.
• Deploy & Scale on Modern Compute: Leverage HPC/GPU clusters and cloud infrastructure to develop, test, and deploy models; champion software engineering best practices (version control, CI/CD, testing, reproducibility, MLOps).

• Use Case Identification & Solution Architecture
• Partner Across Disciplines: Collaborate with drug delivery scientists, device engineers, formulation scientists, CAE/CFD specialists, and product development teams to understand technical challenges and identify high-impact opportunities for scientific ML applications.
• Translate Science to Solutions: Convert complex scientific problems into appropriate mathematical formulations; select optimal modeling paradigms; evaluate trade-offs between model complexity, interpretability, computational cost, and predictive accuracy.
• Design End-to-End Workflows: Architect modeling solutions for device optimization, formulation development, quality prediction, failure mode analysis, and personalized dosing; integrate scientific ML models into broader analytics workflows and decision support systems.

• Decision Support, Leadership Communication & Strategic Impact
• Embed Modeling in the Business: Ensure modeling is tightly coupled to program milestones, risk assessments, and regulatory strategy by partnering with engineering, device design, materials, formulation, human factors, clinical, and quality teams.
• Communicate & Influence: Translate complex scientific ML findings into clear, compelling narratives for both technical experts and business leaders; present modeling insights and recommendations to senior leadership to influence device design, formulation strategies, and development priorities.
• Quantify Value: Develop quantitative business cases demonstrating the value of scientific ML investments in reducing development time, improving product performance, and mitigating risks; create visualizations that effectively communicate model predictions, uncertainties, and actionable recommendations.

• Research Excellence & Continuous Innovation
• Advance State-of-the-Art: Stay current with emerging techniques in scientific ML, physics-informed learning, and computational science; establish a technology roadmap for digital twins, reduced-order models, and multifidelity frameworks.
• Publish & Lead Externally: Publish research findings in peer-reviewed journals and present at scientific conferences to establish thought leadership; drive external collaboration that amplifies internal capabilities and impact.
• Mentor & Raise the Bar: Mentor team members on scientific computing and hybrid modeling approaches; contribute to intellectual property development and competitive differentiation through novel modeling methodologies.

Basic Requirements:

• PhD in Computational Science/Engineering, Applied Mathematics, Physics, Chemical/Mechanical/Biomedical Engineering, or Computer Science (with scientific computing focus)
• 2+ years of experience conducting independent research on applying expertise in both domain physics and machine learning toward technical or business problem solving.
• Expertise in strategic thinking and problem framing
• Experience promoting cross-functional collaboration in a matrix organization
• A growth mindset with a passion for learning, emerging technologies, and working across disciplines.

Additional Preferences:

• Expert-level proficiency in theory and application of at least one physics-based method (e.g., molecular dynamics, CFD, FEA) and foundational knowledge of machine learning / deep learning frameworks.
• Proficiency with Python and scientific computing libraries (NumPy, SciPy, PyTorch/TensorFlow/JAX); experience with HPC environments (MPI, GPU/CUDA).
• Experience in pharmaceutical, medical device, biotechnology, or healthcare industries.
• Understanding of drug delivery mechanisms, pharmacokinetics/pharmacodynamics, transport phenomena, or materials science.
• Breadth across scientific machine learning (ML) methods: PINNs, operator learning (DeepONets, FNOs, GNOs), multifidelity surrogates, Gaussian processes, active learning, and Bayesian UQ/calibration for parameter inference and decision support.
• Experience with ASME V&V 40 and model risk classification
• Familiarity with verification, validation, and regulatory submissions for modeling evidence.
• Hands-on experience with common tools (illustrative, not prescriptive) in the following areas: MD tools (LAMMPS, GROMACS, OpenMM); CFD/FEA tools (OpenFOAM, COMSOL, Abaqus, Ansys); ML frameworks (PyTorch, TensorFlow, JAX, scikit-learn); workflow/computing (MATLAB, Julia, CUDA, Slurm, Azure/AWS, Git, containers, CI/CD); data tools (Pandas, MLflow, DVC).
• Evidence of linking modeling to business value — portfolio decisions, design tradeoffs, robustness/DFM, cost/schedule risk reductions.
• Excellent communication (visualization, scientific storytelling) and a record of peer-reviewed publications and conference presentations.

Other Information:

• Travel up to 10%
• Position: Indianapolis, IN; Lilly Technology Center – North (LTC-N)

Lilly is dedicated to helping individuals with disabilities to actively engage in the workforce, ensuring equal opportunities when vying for positions. If you require accommodation to submit a resume for a position at Lilly, please complete the accommodation request form for further assistance. Please note this is for individuals to request an accommodation as part of the application process and any other correspondence will not receive a response.

Lilly is proud to be an EEO Employer and does not discriminate on the basis of age, race, color, religion, gender identity, sex, gender expression, sexual orientation, genetic information, ancestry, national origin, protected veteran status, disability, or any other legally protected status.

Our employee resource groups (ERGs) offer strong support networks for their members and are open to all employees. Our current groups include: Africa, Middle East, Central Asia Network,