134K–252K USD / year
Machine Learning Scientist – Generative Molecular Design
Machine learningRemote — United States
Published on 2026-10-26
These details were extracted automatically from the original listing. They may not be complete or fully up to date — it's worth checking the original job post.
About this role
Build and optimize generative machine-learning models for discovering materials that meet multiple property objectives. The role spans model development, reward integration, data quality, and deploying production-ready tools for discovery scientists.
About the company
SandboxAQ leverages artificial intelligence and quantum technology to improve decision-making processes across various sectors, including life sciences and medical devices. The company focuses on developing innovative solutions that address complex challenges in data analysis, research, and product management.
The team
AI Simulation division, within the AI Sim and ChemSim teams.
Stack
PyTorchTensorFlowJAXGoogle Cloud PlatformAWS
What you'll do
- Architect and improve the generative platform for material discovery.
- Implement and optimize generative models, including diffusion, flow-matching, GFlowNets, and LLM- or agent-based methods.
- Integrate learned property predictors and simulation oracles as generation rewards.
- Develop computational workflows to generate and evaluate material hypotheses.
- Identify data sources and manage data ingestion, quality control, and validation.
- Deploy models as production tools for discovery scientists.
What we're looking for
- At least 4 years of hands-on experience delivering generative or applied ML for material discovery.
- Ability to write clean, maintainable, production-grade code.
- Experience building scalable ML systems with PyTorch, TensorFlow, or JAX.
- Familiarity with cloud platforms for compute, data processing, and storage.
- PhD or MSc in computational chemistry, physics, computer science, or equivalent.
- Experience developing ML code collaboratively using modern software engineering practices.
- Strong communication and cross-functional collaboration skills.
Nice to have
- Active learning and Bayesian optimization for design-make-test loops using expensive simulations or lab assays.
- Guided generative modeling, chemical-space constraints, inference-time steering, or model fine-tuning.
- Agentic or LLM approaches to material discovery.
Benefits
- Equity and performance-based incentives.
- Health, dental, and vision insurance.
- 401(k) with company match.
- Generous parental leave and PTO.
- Flexible work arrangements.
- Learning budget, mentorship, and professional development opportunities.