Machine Learning Engineer
Pinnacle Medicines
•
Doylestown, PA
0
0
0
0
Mid-Senior level
Posted April 2, 2026
Job link
Thinking about this job
Responsibilities
Responsibilities
- Develop and deploy generative and predictive machine learning models for peptide design, including sequence, structure, and property prediction
- Build and maintain property prediction models that track experiments and generate actionable insights
- Integrate ML models into existing cheminformatics and computational chemistry pipelines, with an emphasis on scalability and reproducibility
- Develop workflows that scale across heterogeneous HPC environments (on-premise and cloud)
- Build and maintain CI/CD pipelines for model testing and deployment
- Implement advanced data curation and splitting strategies that go beyond standard random sampling to prevent data leakage
- Track the latest developments in AI-based protein and molecular design, evaluating new methods for internal adoption Qualifications
Not Met Priorities
What still needs stronger evidence
Requirements
- Develop workflows that scale across heterogeneous HPC environments (on-premise and cloud)
- Implement advanced data curation and splitting strategies that go beyond standard random sampling to prevent data leakage
- Track the latest developments in AI-based protein and molecular design, evaluating new methods for internal adoption Qualifications
- Bachelor's degree or higher in Computer Science, Applied Mathematics, Computational Chemistry, or a related field, with 3+ years of industry experience developing ML applications
- Deep understanding of the mathematical foundations and architectures underlying modern ML models for molecular and protein design (e.g., VAEs, transformers, GNNs, diffusion models, equivariant networks)
- Experience with fine-tuning techniques to adapt large, pre-trained models for specialized tasks
- Fluency in Python and familiarity with ML frameworks used in scientific computing (e.g., PyTorch, JAX, or TensorFlow)
- Familiarity with cheminformatics and structural biology libraries (e.g., RDKit, DeepChem, Biopython, or equivalents)
- Excellent communication skills with the ability to convey complex computational concepts to scientists across disciplines Preferred
- Experience in a fast-paced biotech or startup environment
- Familiarity with physics-based molecular simulations, including docking, MD, and free energy methods
Preferred Skills
- Experience with fine-tuning techniques to adapt large, pre-trained models for specialized tasks
- Fluency in Python and familiarity with ML frameworks used in scientific computing (e.g., PyTorch, JAX, or TensorFlow)
- Familiarity with cheminformatics and structural biology libraries (e.g., RDKit, DeepChem, Biopython, or equivalents)
- Excellent communication skills with the ability to convey complex computational concepts to scientists across disciplines Preferred
- Familiarity with physics-based molecular simulations, including docking, MD, and free energy methods
Education
- (Not required) – Bachelor's degree or higher in Computer Science, Applied Mathematics, Computational Chemistry, or a related field, with 3+ years of industry experience developing ML applications
About the Role We are seeking a creative and driven ML Engineer to help advance PinSilico—our AI and physics-powered peptide discovery platform. This role sits at the intersection of machine learning, computational chemistry, and scientific software engineering at the forefront of drug discovery. You will learn directly from seasoned drug hunters across chemistry, biology, and computation, gaining firsthand exposure to how new medicines are discovered and developed for patients. This is a high-impact, foundational hire shaping the core of our computational platform. Responsibilities
Develop and deploy generative and predictive machine learning models for peptide design, including sequence, structure, and property prediction
Build and maintain property prediction models that track experiments and generate actionable insights
Integrate ML models into existing cheminformatics and computational chemistry pipelines, with an emphasis on scalability and reproducibility
Develop workflows that scale across heterogeneous HPC environments (on-premise and cloud)
Build and maintain CI/CD pipelines for model testing and deployment
Implement advanced data curation and splitting strategies that go beyond standard random sampling to prevent data leakage
Track the latest developments in AI-based protein and molecular design, evaluating new methods for internal adoption Qualifications
Bachelor's degree or higher in Computer Science, Applied Mathematics, Computational Chemistry, or a related field, with 3+ years of industry experience developing ML applications
Deep understanding of the mathematical foundations and architectures underlying modern ML models for molecular and protein design (e.g., VAEs, transformers, GNNs, diffusion models, equivariant networks)
Experience with fine-tuning techniques to adapt large, pre-trained models for specialized tasks
Fluency in Python and familiarity with ML frameworks used in scientific computing (e.g., PyTorch, JAX, or TensorFlow)
Familiarity with cheminformatics and structural biology libraries (e.g., RDKit, DeepChem, Biopython, or equivalents)
Excellent communication skills with the ability to convey complex computational concepts to scientists across disciplines Preferred
Experience in a fast-paced biotech or startup environment
Familiarity with physics-based molecular simulations, including docking, MD, and free energy methods
Develop and deploy generative and predictive machine learning models for peptide design, including sequence, structure, and property prediction
Build and maintain property prediction models that track experiments and generate actionable insights
Integrate ML models into existing cheminformatics and computational chemistry pipelines, with an emphasis on scalability and reproducibility
Develop workflows that scale across heterogeneous HPC environments (on-premise and cloud)
Build and maintain CI/CD pipelines for model testing and deployment
Implement advanced data curation and splitting strategies that go beyond standard random sampling to prevent data leakage
Track the latest developments in AI-based protein and molecular design, evaluating new methods for internal adoption Qualifications
Bachelor's degree or higher in Computer Science, Applied Mathematics, Computational Chemistry, or a related field, with 3+ years of industry experience developing ML applications
Deep understanding of the mathematical foundations and architectures underlying modern ML models for molecular and protein design (e.g., VAEs, transformers, GNNs, diffusion models, equivariant networks)
Experience with fine-tuning techniques to adapt large, pre-trained models for specialized tasks
Fluency in Python and familiarity with ML frameworks used in scientific computing (e.g., PyTorch, JAX, or TensorFlow)
Familiarity with cheminformatics and structural biology libraries (e.g., RDKit, DeepChem, Biopython, or equivalents)
Excellent communication skills with the ability to convey complex computational concepts to scientists across disciplines Preferred
Experience in a fast-paced biotech or startup environment
Familiarity with physics-based molecular simulations, including docking, MD, and free energy methods