AI Research Scientist/ Research Engineer: Materials Discovery

Logical Intelligence • San Francisco, CA

5h

About The Position

Logical Intelligence is hiring for its materials discovery team to build AI systems that propose and evaluate candidate molecules and support an iterative discovery loop with partner labs. The role focuses on developing energy-based models that incorporate learned representations with physical and chemical knowledge, improving how the system searches chemical space, and selecting molecules for testing. The scientist or engineer will work closely with chemists, physicists, machine learning researchers, engineers, and laboratory partners. Synthesis and measurement results will be used to evaluate and improve the models.

Requirements

• Background in machine learning, computational chemistry, physics, or a related field.
• A PhD, or a Master’s degree plus relevant industry experience.
• Hands-on experience building machine-learning models for real scientific problems.
• Familiarity with energy-based models, diffusion or score-based models, or similar generative approaches, and interest in developing further expertise.
• Knowledge of chemistry or a genuine interest in learning it alongside chemists.
• Experience designing evaluations and experiments that correlate with downstream performance.
• A record of impactful research demonstrated through publications, patents, open-source software, or methods used in real discovery programs.
• Excellent scientific writing and communication skills, and comfort working in an interdisciplinary team.

Nice To Haves

• Hands-on research experience with energy-based models or methods that combine learning with search and optimization.
• Experience with molecular machine learning, such as property prediction, generative molecular design, machine-learning interatomic potentials, or quantum-chemistry workflows such as DFT.
• Experience with closed-loop design using real laboratory feedback.

Responsibilities

• Build and improve AI systems for the discovery loop, including candidate generation, screening, and selecting which molecules to test next.
• Develop energy-based models that combine learned representations with physical and chemical knowledge to search chemical space more efficiently.
• Own model evaluation, including held-out chemical-family benchmarks, accuracy against quantum-chemistry calculations and experiments, uncertainty calibration, prospective testing, and tracking across model versions.
• Compare AI predictions with measurements, investigate disagreements, and translate findings into concrete model changes in collaboration with AI researchers and engineers.
• Design experiments with partner laboratories so each round of synthesis and testing is as informative as possible.

What This Job Offers

• Job Type: Full-time