Machine Learning Scientist – Generative Molecular Design

The role

You will build and optimize a generative engine for material discovery. This involves implementing generative architectures, managing reward interfaces, and handling data for model training and production.

What you will do

• Architect and evolve the flagship generative platform.
• Implement and optimize state-of-the-art generative models.
• Own the reward interface by integrating learned surrogates and simulation-derived oracles.
• Develop and deploy computational methods and workflows to generate and evaluate hypotheses.
• Identify relevant data sources and take responsibility for data ingestion, QC, and validation.
• Collaborate daily with ML researchers and broader R&D, discovery, engineering, and product teams.

Required qualifications

• 4+ years of experience building and shipping modern generative or applied ML for material discovery in industry or an equivalent research setting.
• Ability to write clean, maintainable, and robust production-grade code.
• Ability to build scalable ML using PyTorch, TensorFlow, or JAX.
• Familiarity with cloud-based platforms such as Google Cloud Platform or AWS.
• PhD or MSc in Computational Chemistry, Physics, Computer Science, or equivalent.
• Excellent communication skills.
• Experience developing ML code in a collaborative environment using modern software engineering best practices.

Nice to have

• Active learning and bayesian optimization.
• Guided generative modeling for material discovery.
• Agentic and LLM approaches to material discovery.

Benefits

• Comprehensive health, dental, and vision insurance
• 401(k) with company match
• Generous parental leave
• Flexible hybrid work arrangements
• Generous PTO
• Direct exposure to CHIPS Act-funded programs
• Mentorship
• Dedicated learning budgets

About the company

SandboxAQ is a high-growth company delivering AI solutions that address global challenges. The company emerged from Alphabet Inc. as an independent, growth capital-backed company in 2022.