We use AI to discover new pesticides, because the ones we have now are failing — pests keep evolving, and the chemicals kill too many other things (like humans). Our models replace slow, expensive lab work, letting us discover new molecules 100× faster. Our first pesticide targets a Spodoptera with a novel mode of action. We’re a small team of young engineers from Caltech & Wolfram Research, with experience in drug discovery ML models, rebuilding agrochemical R&D around AI.

We’re building a system that replaces a lab technician + physics + chemistry intuition with a single neural network. This is a rare role: someone who can operate like a strong SWE/MLE while also being a real synthetic chemist with biochemistry depth (proteins/peptides). You’ll work directly with the founders to connect model predictions to molecules we can actually make, generating the data loop that makes our models better over time.

We’re willing to pay a $15k referral bonus for an exceptional hire.

What You’ll Work On

• Own our data pipeline end-to-end: ingest data from lab/CROs/vendors/journals, enforce reproducible protocols + metadata standards, and maintain a central database that’s easy to query and iterate on.
• Make our generative / synthesis models chemistry-aware and tightly integrated with what we can actually make in the lab.
• Help design new peptides and small molecules and test them in the lab.
• Help build our automated synthetic chemistry + peptide synthesis lab from scratch, including vendor/CRO coordination and workflows that generate ML-useful data.

Requirements

• Strong SWE fundamentals: excellent Python, clean engineering habits, reproducible workflows, and comfort running and training ML models.
• Experience building data pipelines and datasets for ML (SQL).
• Synthetic chemistry experience including retrosynthesis and practical route planning.
• Solid biochemistry / molecular design foundation, with hands-on experience in peptide/protein synthesis and/or protein/peptide design, or strong small-molecule design experience.
• High ownership and speed in an ambiguous, fast-moving startup environment.

Nice to Have

• Experience designing automated synthetic chemistry labs.
• Deep ML research experience.
• Mandarin Chinese fluency (our lab will be built in China, and many of our CRO’s are Chinese)

What We Offer

• Work directly with both founders on core technical decisions.
• Ownership across models, data, and lab execution — the full loop.
• A mission that matters: safer, more targeted pest control through better science and better models.

We use Python + PyTorch to build AI models that predict how well molecules will do at killing a pest and nothing else. We use these models to search through billions of possible compounds. Model accuracy and data quality are problems we're always iterating on. Another hard part is choosing which molecules to test in physical reality for data feedback — we're using ideas from information theory and reinforcement learning to pick the highest utility tests, trading off cost and time. On the bio side, we work on designing effective assays that are conducive to large scale data collection for ML, as well as optimizing the process of in-vivo testing on our target pest. Minimizing time between test results is a big priority. Long term, we’re building a general system that can design any molecule for a given task using AI.