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 fundamentally building a system that replaces a lab technician + physics with a single neural network. This role exists to help build the backbone of that: building foundational biochemistry models and the continuous data feedback loop between model predictions and physical experiments. This role doesn’t require biology knowledge, just solid fundamentals in machine learning. 

What you’ll work on:

• Use your understanding of machine learning to develop models foundational to eventually replacing the need for wet-lab experiments. 
• Design, train, and refine foundational biomolecular interaction models (architecture design)
• Assemble high-quality training data and build autonomous data collection systems.
• Analyze the generalization and weaknesses in our models to inform data-generation strategy. 
• Lead the design of future models to replace every part of chemical R&D.

Requirements:

• Solid practical ML engineering and software engineering fundamentals (Python, PyTorch/JAX/TensorFlow, NumPy/SciPy)
• Proven track record of designing, building, and validating novel ML model architectures and training techniques.
• Strong foundation in mathematics, algorithms, statistics, and data science principles.
• Familiar with SQL and building datasets for ML.

Nice to have:

• Experience working with biochemical or structural biology datasets
• Exposure to foundation models in bio (e.g., AlphaFold, ESM, RoseTTAFold, ProtBert).
• Experience working with LLM agents
• Experience managing large training runs on GPU clusters.

What we offer:

• Work directly with both founders in a small highly technical fast paced ML engineering team
• Ownership of foundational ML infrastructure and research
• A mission that matters: enabling a safer, more sustainable future in agriculture through 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.