Edison Scientific

Scientific Evals

San Francisco, CA

Sponsorship not specified$160k-$300kDetected 137 days ago

PythonMachine LearningDeep LearningLLMsAgentic AIBioinformaticsResearchCollaboration

About the role

Scientific discovery moves too slowly, and autonomous AI agents are how we intend to fix that.
This role sits at the intersection of biology, data curation, and machine learning, and is ideal for someone with deep scientific training who is excited to shape how frontier AI systems learn to do science.
This role is on-site at our San Francisco office in the Dogpatch neighborhood.

Design benchmarks that capture the complexity of real biological research, drawing on your domain expertise to identify what makes scientific reasoning hard.
This will include open-ended scientific benchmarks and building on prior work like LAB-Bench and BixBench.
Collaborate with AI/ML researchers to translate scientific intuition into training signal, helping AI systems learn not just facts but how scientists think.
Coordinate operations and manage workflows, including working with domain experts, tracking task progress, and maintaining documentation.
Edison Scientific builds and commercializes AI agents for science.
We're assembling a team of top researchers and engineers across AI and biology to build an AI scientist.
Our office is a converted warehouse with high ceilings, open space, and a team that genuinely believes in what they're building.

Experience with bioinformatics pipelines, biological databases, or sequence analysis tools.
Publications or research experience in areas relevant to AI for science.
Graduate-level training in biology, biochemistry, computational biology, or a related field, with hands-on research experience.
Working knowledge of machine learning concepts, particularly deep learning and large language models.
Comfortable with Python and building workflows for data processing, analysis, and experimentation.
Possess strong scientific taste and able to identify what distinguishes expert-level reasoning from surface-level pattern matching.
Detail-oriented and willing to take on high-value but occasionally tedious work.
Energized by ambiguous, open-ended problems that require creativity, collaboration, and first-principles thinking to solve.
Organized and communicative, able to manage multiple workstreams and coordinate across teams.
Bonus points for
Prior experience creating evaluation datasets, annotation guidelines, or working on human-in-the-loop data pipelines.
Hands-on experience fine-tuning or evaluating large language models, or familiarity with RLHF and preference-based training.

Full healthcare coverage - we pay 100% of premiums for you and your dependents
Support for growing families, including a yearly new parent stipend and fertility coverage through Carrot
$300 health and wellness benefit

We are seeking an ambitious, scientifically grounded person to join our team focused on developing rigorous benchmarks and training datasets that advance AI capabilities in biology.
This position is part of the Evals team.

This listing is sourced directly from Edison Scientific's careers page and normalized into a canonical job model.