🔥 16 hours ago
Build and evaluate biology benchmarks that test whether AI agents can make expert biologics-development decisions, using antibody data to assess quality, developability, pharmacology, and safety.
Latchbio jobs
Browse active jobs at Latchbio.
6 open roles at Latchbio
Sort jobs
🔥 17 hours ago
Set scientific standards for AI microscopy benchmarks by curating imaging datasets, building verifiable ground truth, adjudicating ambiguous evidence, and evaluating whether agent reasoning meets expert standards.
🕒 4 days ago
Lead scientific benchmarking for biology AI models by designing benchmark tasks and quality standards, mentoring a team of up to seven scientists, and partnering with engineering and leadership to scale production and tools.
🕒 6 days ago
Set scientific standards for AI neuroscience benchmarks by designing realistic research tasks, curating multimodal evidence, and evaluating whether agents’ reasoning and conclusions meet expert standards.
📅 Aug 13
Evaluate how AI agents analyze complex microbiome and metagenomics datasets by building ground-truth benchmarks from published studies, defining whether agents can perform expert-level analytical and interpretive tasks.
📅 Jul 10
Set scientific standards for AI agents in proteomics by designing benchmark tasks, curating mass spectrometry datasets, and evaluating whether agent conclusions reflect sound expert reasoning.
Page 1 · 6 results