Software Engineer, Data & ML

the company | Software Engineer, Data & ML | On-Site (Cambridge, MA) | Full Time | $105,000–$130,000 + equity

Foray is a plant production company using plant cells, artificial intelligence, and advanced biomanufacturing to grow materials, molecules, and seeds directly from the cell up.

Our work is powered by Pando, our intelligent workspace for plant science. Pando combines novel plant datasets and emerging predictive models to help researchers design and optimize plant production workflows with greater speed and reliability. Together, our software and biomanufacturing platforms are creating new ways to produce what we need from plants while building more resilient plant industries.

We’re looking for a Software Engineer, Data & ML to help build the software and data foundation behind Pando. You’ll work across the product, with a particular focus on backend systems, APIs, data infrastructure, and the systems supporting our machine learning work. A major part of the role is figuring out how to turn complex scientific and experimental information — including scientific literature, natural language, and data generated in the lab — into reliable, structured data.

• Strong software engineering generalist with particular depth in backend and data systems
• Experience shipping production-grade software and building backend systems, data pipelines, databases, APIs, or other data-intensive infrastructure
• Strong in Python and comfortable with relational databases, APIs, and modern software systems
• Familiar with MLOps and the infrastructure needed to run AI models in production
• Comfortable turning messy, heterogeneous, or unstructured information into trustworthy data, including through NLP, information extraction, or similar techniques
• Understand good scientific data practices including quality, provenance, versioning, reproducibility, permissions, and access controls
• Enough statistical fluency to reason about experimental data, uncertainty, and design of experiments
• Enjoy learning unfamiliar domains, working across disciplines, and solving ambiguous problems with significant ownership
• Experience with scientific or biological data, ML infrastructure, predictive modeling, optimization, or AI applications is helpful, but we don’t expect one person to have done all of these things before
• Must be authorized to work in the United States