JavaScript is disabled

Are you ready to shape the next generation of AI research in molecular science?

This is a unique opportunity to join a dynamic team at the cutting edge of machine learning research, where you’ll have the chance to design, experiment, and implement groundbreaking models that power large-scale scientific discovery. We are looking for an ML Research Engineer with a passion for solving complex problems, blending research ingenuity with robust engineering skills.

Join a mission-driven, well-funded organization pioneering the convergence of AI and chemistry. By building advanced foundation models for molecular-level biology, they are pushing beyond traditional limits of drug discovery. Operating at massive scale across compute, data, and innovation, this is a place for ambitious minds who value collaboration, creativity, and executional excellence. Here, your impact will span from early-stage ideas all the way to production-level systems used in real-world breakthroughs.

• Strong software engineering fundamentals, including reproducible pipelines and documentation
• Demonstrated contributions in ML or scientific computing (e.g., Git Hub projects or publications)
• Solid working knowledge of PyTorch, JAX, and modern ML research stacks
• Familiarity with large-scale compute environments and high-throughput experimentation
• Scientific depth via industry experience or a relevant PhD

• You will drive research engineering initiatives that explore new frontiers of molecular modeling and simulation.
• Design and execute experiments to test foundation model hypotheses
• Build and maintain robust, scalable libraries for training, evaluation, and simulation
• Implement cutting-edge model architectures from literature and internal research
• Develop meaningful evaluation metrics for rapid iteration and model improvement
• Support research workflows, including manuscripts, datasets, and reproducible tooling

• Programming:
  Python, PyTorch, JAX
• Systems: HPC experience, distributed compute
• Research Development:
  Experimentation frameworks, evaluation methodologies

• Knowledge of geometric deep learning, equivariant models, or GNNs
• Familiarity with generative modeling (diffusion, flow matching, score-based)
• Contributions to open-source projects in ML or scientific computing
• Experience with agent-driven research systems and active learning pipelines