Software Engineer, Scientific Models

San Francisco, United StatesRemote

Responsibilities

- Define standards and tooling for model developers, creating frameworks that make it easy to integrate, test, and ship third-party open-source and proprietary models into Benchling.

We are rebuilding biotech for the AI era.
AI has the potential to change this, compressing decades of R&D work into years.
But that only happens when clean, structured scientific data and AI are built into how science gets done.
Benchling is the AI platform for biotech R&D.
Scientists use Benchling to design experiments, capture structured data, and run AI agents and models directly in their workflows.
ROLE OVERVIEW We’re a team that’s embedding cutting-edge scientific AI models into Benchling to help scientists design better molecules.
It’s early days for scientific AI models, both at Benchling and in the industry at large.
- Shape how we build AI at Benchling, driving experimentation, contributing to technical direction, and helping evolve our engineering and product development practices as the field matures.
experience with backend systems and infrastructure for supporting scientific model training or inference. - Strong technical and analytical skills for optimizing compute-intensive systems. - Collaborative mindset, able to work closely with engineers, product managers, and scientists to bring new ideas to life. - Desire to work in a fast-paced environment, where priorities can shift and rapid experimentation is encouraged.

QUALIFICATIONS - 3+ years of software engineering or equivalent research experience, developing or deploying scientific models in an industry or academic setting. - Strong

Getting a molecule from discovery to patients, or a crop from lab to field, involves thousands of slow, manual, disconnected steps.
Over 200,000 scientists around the world trust Benchling to power their most important work, from academic labs to Sanofi, Moderna, and more than half of the world's top 50 biopharma.
AlphaFold) predict structures, assess properties, and even generate new ideas, acting as a design partner as scientists design life-saving therapeutics and other molecules.
You’ll experiment with the latest models, define standards for model developers to be able to contribute their models, and design our architecture for fast inference.
We’ll rapidly iterate with customers and change directions quickly, figuring out new patterns for how we develop and go to market.
We’ll win if we stay curious and obsess over our customers.
RESPONSIBILITIES - Build and scale our scientific model platform by designing and implementing infrastructure for model inference that is fast, reliable, and cost-effective across a diverse set of scientific models.
- Work directly with customers to ideate use cases, gather feedback, and onboard scientific teams.
HOW WE WORK We offer a flexible hybrid work arrangement that prioritizes in-office collaboration.
Employees are expected to be on-site 3 days per week (Monday, Tuesday, and Thursday). #LI-Hybrid #BI-Hybrid #LI-KW1 Benchling welcomes everyone.