Machine Learning Scientist

No sub-contracting! No C2C. This requires onsite Monday thru Friday

Job description:

Machine Learning Scientist (Contract)

Team: Structure & Simulation
Organization: Research & Early Development

The Structure & Simulation team develops advanced computational methods to accelerate therapeutic discovery within a leading bio-pharmaceutical research organization. Our work spans molecular generation, compound scoring and prioritization, exploratory biological simulation, and acceleration of physics-based modeling enabling data-driven decision-making from early discovery through experimental validation.

We are seeking a highly motivated Machine Learning Scientist to design innovative scientific methodologies and deliver production-ready workflows that support both computational and experimental scientists. This role involves close collaboration across multidisciplinary research teams to advance the understanding and design of bio-molecular systems.

Key Responsibilities

• Develop machine learning methodologies for the understanding, scoring, ranking, generation, and design of bio-molecules, with a particular focus on proteins.

• Engineer robust, scalable scientific software that integrates into lab-in-the-loop research workflows.

• Contribute to and maintain collaborative codebases using best practices (version control, automated testing, modular design, documentation).

• Deploy and optimize workflows on high-performance computing (HPC) and cloud platforms.

• Develop intuitive, web-based interfaces to enable researchers and medicinal chemists to apply advanced computational tools in their daily work.

Required Qualifications

• BS, MS, or PhD in life sciences, physical sciences, computer science, or a related discipline.

• Strong expertise in Python and scientific software development.

• Experience deploying software workflows on cloud and/or HPC infrastructure.

• Experience contributing to collaborative codebases, including code review, testing, and version control workflows.

• Self-motivated, independent, and comfortable working in cross-functional environments.

• Strong communication and interpersonal skills.

• Working knowledge of modern machine learning techniques, including predictive modeling, generative models, and active learning applied to molecular design and optimization.

Preferred Qualifications

• Public portfolio of relevant projects (e.g., GitHub).

• Experience with molecular modeling or computational chemistry platforms (e.g., Rosetta, OpenMM).

• 3+ years of industry experience.

• Experience working with large-scale chemical and biological datasets, including graph-, sequence-, and structure-based data.