Staff Machine Learning Research Scientist, SandboxAQ

• World-Class Domain Expertise: PhD in Computer Science, Computational Chemistry, or a related field, with specific focus on structure-based deep learned affinity modelling a plus
• Proven Industrial Impact: At least 4 years of post-PhD experience, including experience in a professional industry setting, with a track record of delivering scientific impact that translates to product
• Frontier Technical Skills: Direct, hands-on experience developing and executing leading-edge co-folding and/or affinity prediction models, from proof of concept to productionized workflows
• Domain-Specific Excellence: Proven excellence in co-folding and/or affinity prediction, as demonstrated by participation in industrial projects and/or academic publications
• Professional Engineering Fluency: Experience functioning within a professional software team, including proficiency in Python and modern ML frameworks (PyTorch/JAX) at scale

Desirable

• The AI Sim R&D team creates leading edge ML and physics-based models ("LQMs") to advance drug and materials discovery
• We are a flexible, creative, and impact driven team of multidisciplinary scientists and engineers, whose products dramatically accelerate the creation of molecules and medicines
• As a Staff ML Research Scientist focusing on Co-Folding & Affinity, you will occupy a senior position architecting our ML biopharma capabilities
• Your central purpose is to redefine the state-of-the-art in structure prediction and binding affinity, transforming these breakthroughs into core components of our software suite
• Within your first year, you will: pioneer novel deep learning architectures that surpass current benchmarks, orchestrate the seamless integration of these models into production-ready drug discovery pipelines, and solidify SandboxAQ’s scientific authority through high-impact publications and industry-shaping research
• Pioneer Novel Architectures: Drive the research and development of next-generation deep learning models for protein-ligand co-folding and affinity prediction
• Architect Product Integration: Bridge from research to commercial utility by equipping SandboxAQ’s software products with advanced predictive capabilities
• Orchestrate Technical Strategy: Bring novel ideas and the content of scientific papers into the ideation, training, and benchmarking of complex models, ensuring they are optimized for large-scale, real-world drug discovery applications
• Champion Scientific Excellence: Act as a technical beacon for the team, representing SandboxAQ scientifically and shaping its vision externally and internally
• Scale High-Performing Teams: Mentor junior researchers and collaborate across engineering and product teams to foster a culture of technical rigor and rapid iteration