Nanofacile - Machine Learning Specialist

Role and Responsibilities

The Machine Learning Scientist will play a key role in designing and deploying predictive and optimization models that power Nanofacile’s Formulation Companion. This role focuses on transforming experimental formulation data into intelligent guidance for researchers, enabling faster iteration, improved formulation success rates, and scalable learning across targeted encapsulated therapy campaigns.

Key Responsibilities

• •Designing, training, and evaluating machine learning models to predict formulation outcomes (e.g., particle size, PDI, encapsulation efficiency, stability, transfection efficiency).
• •Developing optimization and recommendation systems to propose improved formulations based on historical experiments and constraints.
• •Building and maintaining clean, reproducible ML pipelines (data processing, feature engineering, training, evaluation, versioning).
• •Collaborating with scientists and engineers to translate formulation workflows into structured datasets suitable for modeling.
• •Supporting the integration of ML models into production systems (APIs, webapp features, internal tools).
• •Designing interpretable model outputs and scientific explanations to build user trust and adoption. ● Contributing to validation strategies and experimental design to improve dataset quality and reduce noise.
• •Writing clean, maintainable, and well-documented code.
• •Conducting code reviews and ensuring best practices across ML-related contributions.

Qualifications / Competencies

• •Ph.D. or Master’s degree in Machine Learning, Computer Science, Bioinformatics, Computational Chemistry, Biomedical Engineering, or related field.
• •Strong proficiency in Python and ML tooling (scikit-learn, PyTorch, XGBoost, etc.).
• •Familiarity with model deployment patterns (FastAPI, Docker, cloud deployment, or similar)
• •Experience with structured experimental datasets, including cleaning, normalization, missing data handling, and QC.
• •Strong statistical foundations and experience with experimental noise and reproducibility challenge
• •Excellent problem-solving skills and ability to work in a fast-paced startup environment.
• •Strong communication skills and ability to collaborate across scientific and engineering teams

Nice to Have

• •Experience with Bayesian optimization, active learning, or surrogate modeling
• •Exposure to cloud environments (AWS, GCP, or Azure)
• •Exposure to RNA delivery, lipid nanoparticles (LNPs), formulation science, or biophysical modeling ● Experience building recommendation systems, similarity search, or constraint-based optimization tools.