You will act as the scientific authority to evaluate and benchmark AI agents on their ability to reason through complex biological workflows and longevity research. This involves curating datasets, designing rigorous tasks, and adjudicating longevity claims to ensure AI outputs meet expert standards.
You will design and validate benchmarks for AI agents by creating clinical imaging studies and evaluating agent performance against expert standards. This involves defining optimal answer formats, reviewing agent interpretations, and ensuring clinical soundness in AI-driven diagnostic workflows.
You will contribute to the technical approach for evaluating AI agents in diagnosing, treating, and researching rare and progressive diseases. This involves building ground-truth benchmark datasets that test whether AI agents can perform complex analytical and interpretative tasks.
You will contribute to the technical evaluation of AI agents across the genetic medicines pipeline, including gene therapy, gene editing, and RNA therapeutics. This involves designing program case studies, reviewing scientific soundness of agent outputs, and calibrating agent performance on preclinical data.
You will act as the scientific authority to build and validate immunology-based tasks and datasets for AI agent benchmarking. This involves interpreting raw immune data, setting gold-standard answers, and challenging AI conclusions against expert biological review.
You will act as the scientific authority to build and validate benchmarks for AI agents in vaccine, antibody, and antiviral development. This involves transforming complex biological workflows into gradable tasks and judging agent performance against expert standards.
Design scientific evaluations to test AI agents' ability to solve complex problems in human biology and disease. Analyze experimental and clinical data to establish reliable ground truth for benchmarking AI performance.
You will act as the scientific authority to evaluate and benchmark AI agents on complex structural biology tasks, ensuring their reasoning aligns with expert standards. This involves building datasets, defining gold-standard answers, and collaborating with engineers to refine AI performance across various structural modalities.
You will act as the scientific authority to build tasks and datasets that benchmark AI agents in peptide discovery workflows. This involves curating real-world experimental data and setting rigorous standards for agent reasoning and accuracy.
You will act as the scientific authority to define expert reasoning for imaging tasks and build gold-standard datasets for AI benchmarks. Additionally, you will partner with software engineers to develop analysis pipelines and adjudicate ambiguous biological images to ensure high-quality ground truth.
You will act as the scientific authority to define expert reasoning and build rigorous benchmarks for AI agents in neuroscience. This involves designing research scenarios, curating multi-modal datasets, and adjudicating agent performance against expert standards.
You will contribute to the technical approach for evaluating how AI agents reason through complex microbiome and metagenomics datasets. Additionally, you will collaborate with engineers and biologists to build ground-truth benchmark datasets that test the analytical capabilities of AI agents.
Contribute to the technical approach of teaching AI agents to understand and handle complex genomic and proteomic data. Work across end-to-end data analysis workflows from instrument outputs to scientific decision-making.
