Bindwell, a Y Combinator-backed startup based in San Francisco, is on a mission to reinvent pesticide discovery through artificial intelligence. The company seeks a founding machine learning engineer to help build neural networks that mimic and eventually replace traditional lab techniques in biochemistry, streamlining the research and development of safer, more effective pest control compounds. By leveraging custom models, Bindwell aims to drastically speed up the process of identifying new molecules, targeting persistent pest challenges with innovative approaches that move beyond outdated chemical solutions.
The role offers direct collaboration with Bindwell’s founders—a team with backgrounds at Caltech and Wolfram Research, bringing expertise in drug discovery machine learning and computational biology. The engineer will design, train, and refine biomolecular interaction models, assemble high-quality datasets, implement autonomous data pipelines, and lead the generalization and weaknesses analysis critical to model improvement. Rather than demanding deep biology knowledge, the position emphasizes robust machine learning and software engineering fundamentals, with proficiency in Python, PyTorch/JAX/TensorFlow, NumPy/SciPy, and SQL as essential requirements. Experience with foundation models in biology—such as AlphaFold or RoseTTAFold—working with large-scale GPU clusters, and using large language model agents are highly desirable, but not mandatory.
Bindwell distinguishes itself by replacing labor-intensive, expensive lab work with rapid computational predictions, reportedly accelerating molecule discovery by up to 100 times. The startup addresses the mounting problem of evolving, resistant pests and the unintended harm of legacy pesticides. Their first product targets a Spodoptera pest with a novel mechanism of action. Besides technical ownership and speed, Bindwell puts strong emphasis on its mission: creating a more sustainable agricultural future made possible by advanced modeling, enabling safer and more efficient crop protection. Candidates will join a compact, technically driven team at a pivotal stage, shaping the infrastructure and future direction of proprietary artificial intelligence-driven agricultural innovation.
