Research Engineer, Model Evaluation and Improvement
San Francisco, CA$136.4k - $265.1kFull-timePosted 2mo ago
About the role
Role focused on building datasets, evaluations, and systems to improve frontier AI models for scientific tasks in biology, working at the intersection of software engineering, biology, and frontier AI.
Responsibilities
- Build datasets for evaluating and improving frontier models, turning complex scientific data into high-quality tasks and environments for LLMs.
- Analyze model failure modes, running experiments across frontier models to understand where they struggle and identify opportunities for improvement.
- Build scalable data infrastructure, creating pipelines that curate, transform, and validate large volumes of scientific data into tasks for model evaluation and improvement.
- Collaborate with frontier AI labs, helping develop and evaluate new approaches for improving models on challenging scientific tasks.
- Work closely with scientists, translating expert judgment into problems and evaluation criteria that can reliably distinguish strong model behavior.
Qualifications
- 2+ years at the intersection of biology and AI, with experience evaluating and improving scientific models or LLMs for biological applications.
- Experience building with LLMs, with an intuition for where current models excel, where they struggle, and how to design systems around their capabilities.
- Curiosity and excitement about frontier AI, with a desire to understand and push the capabilities of rapidly improving models.
- Comfort working on ambiguous problems, where the playing field is rapidly shifting and the right technical approaches are still being discovered.
- Collaborative mindset, able to work closely with engineers, scientists, and external research partners.
- Desire to work in a fast-paced environment, where priorities can shift and rapid experimentation is encouraged.
Skills
Required:Biology + AI intersection experienceLLM development and evaluationData pipeline and infrastructure
Benefits
- Full-time U.S. employees enjoy a comprehensive benefits program including equity, health, dental, vision, 401(k)+ employer match, wellness, commuter, and more.
Last updated Sep 3, 2026. Interested? Apply on the company site.
About Benchling
Cloud-based platform for biotech R&D | Benchling
Benchling is a cloud-based platform for biotechnology research and development and the only biology-first platform for scientific data, collaboration, and insights.
BioresearchBioprocessIn VivoConnectGene therapyCell therapyAntibodies and proteinsRNA therapeutics
More open roles at Benchling
- Enterprise Account Executive4d agoRemote · Sales
- Enterprise Account Executive4d agoRemote · Sales
- Product Manager, Study Lifecycle4d agoHybrid (Boston, MA) · Product & Design
- Solution Consultant - R&D1w agoRemote · Sales
- Solution Consultant - R&D1w agoHybrid (Zurich, Switzerland) · Sales