> Markdown version of [/jobs/ext/4328928-principal-senior-scientist-lnp-discovery-machine-learning](https://www.wearedevelopers.com/jobs/ext/4328928-principal-senior-scientist-lnp-discovery-machine-learning). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # (Principal / Senior) Scientist, LNP Discovery & Machine Learning - **Company:** LAZARUS LLC - **Location:** Somerville, MA, United States - **Experience:** Expert - **Salary:** $165,000.0 - $195,000.0 - **Contract:** Permanent contract - **Skills:** Computer Programming, Information Leak Prevention, Python (Programming Language), Machine Learning, Scientific Computating, Pytorch, Pandas, Scikit Learn, Multi-objective Optimization - **Published:** October 5, 2026 - **Apply:** https://www.indeed.com/viewjob?jk=f690f607d37c76ae ## About the Role * PhD in drug delivery, chemical engineering, bioengineering, pharmaceutical sciences, chemistry, or a related field, typically with five or more years of relevant postdoctoral or industry experience for the Principal Scientist level. * Deep hands-on experience developing LNPs or closely related nanoparticle systems. * Strong experience with formulation development, particle characterization, mammalian cell culture, and quantitative delivery assays. * A track record of independently developing or materially improving a nanoparticle delivery workflow. * Strong quantitative and programming skills. * Experience applying machine learning to chemical, formulation, or biological datasets. * Experience with Python and relevant scientific computing tools such as pandas, scikit-learn, RDKit, PyTorch, BoTorch, or equivalents. * Experience with sequential experimental design, active learning, Bayesian optimization, or related methods in which model outputs directly informed experiments. * Strong judgment around assay quality, controls, replication, batch effects, uncertainty, and data leakage. * Ability to lead a scientific program while remaining active at the bench and in code. Particularly relevant experience - Extrahepatic delivery, lung-targeted LNPs, lipid chemistry, primary-cell screening, automated formulation, endosomal escape assays, high-content imaging, IVIVC/IVIVE, process development, formulation scale-up, or transfer of research formulations into reproducible production processes. ## Description Lazarys is hiring a Principal or Senior Scientist to lead LNP discovery for our systemic mRNA programs. You will develop and optimize proprietary LNP formulations for systemic delivery, with an initial focus on extrahepatic expression, including the lung and tumor tissue. This role combines formulation science with quantitative modeling: you will design formulation campaigns, generate high-quality experimental datasets, build predictive models, and use those models to inform subsequent rounds of testing. This is a hands-on leadership role. You will report to the CSO and supervise a Senior Research Associate focused on formulation and assay automation. About Us - Lazarys is developing medicines for solid tumors across RNA and cell therapy. Our lead program is an intravenously administered mRNA therapeutic for advanced non-small cell lung cancer. We are developing delivery systems, tumor-selective expression control, and engineered therapeutic proteins intended to increase activity in tumors while limiting exposure in healthy tissues. We are an early-stage team based in Somerville, Massachusetts, with much of our experimental work performed in-house. Responsibilities - * Design and execute LNP formulation campaigns across ionizable lipids, helper lipids, sterols, PEG lipids, composition, N ratio, mixing conditions, buffers, purification, concentration, and storage. * Develop formulations for systemic mRNA delivery with an emphasis on productive extrahepatic expression, tolerability, reproducibility, and manufacturability. * Establish and maintain characterization methods for particle size, PDI, RNA encapsulation, RNA integrity, apparent pKa, and stability. * Develop cell-based screens across tumor and normal-cell models. * Evaluate productive delivery, not simply cellular uptake. * Work closely with in vivo pharmacology to compare formulation properties and in vitro performance with biodistribution, tissue expression, and tolerability. * Determine which in vitro measurements are most predictive of in vivo performance. * Develop predictive models for formulation data using Python. * Apply active learning, Bayesian optimization, multi-objective optimization, or related approaches to experimental selection. * Prospectively compare model-selected formulations with appropriate experimental baselines. * Improve formulation reproducibility, RNA recovery, stability, material consumption, and cost. * Supervise and develop the Senior Research Associate supporting formulation and automation.