At LatchBio, we're building agents that help thousands of scientists analyze and interpret data from the next generation of spatial and multi-omic tools in biotech. Our agents can store terabytes of data, visualize millions of cells, and orchestrate hundreds of computers towards bio-computational ends. Teams at pharmaceutical, biotech, and solution provider companies rely on our technology to enhance, inform, and deliver the future generations of biological products. We introduced SpatialBench, the first benchmark suite for spatial biology agents — 146 verifiable problems drawn from real industry and academic analysis workflows across five spatial platforms. Our findings show that harness design — the tools, prompts, and control flow around a model — moves outcomes as much as swapping the base model itself. We have subsequently released scBench, and are working on benchmarks and benchmarking infrastructure for 5+ more important areas of biology. Our persistence is leading to market validation. In the past year (April 25 to April 26), we have grown our revenue over 6x. More importantly for our long term growth, we have a repeatable sales process and have more demand than we can meet. We are rapidly scaling our team across many areas, including engineering. Here is a sample of engineering products we work on Agent harness integrated with bio first tooling such as an in-house h5ad and genomics viewer Distributed file-system with metadata on Postgres and blobs on S3 Cluster orchestrator designed to accept compute nodes from anywhere on the internet Reactive Python-based notebooks for data analysis and visualization Benchmarking harness with automated QC processes to validate and probe model failure cases. You will be working on problems in software, including but not limited to web development, systems programming, database administration, cloud infrastructure, agent harness engineering, model benchmarking, and benchmark construction. Engineers are given enormous responsibility and creative freedom over the design and implementation of systems. The tools and features we ship immediately impact the daily workflows of hundreds of scientists.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
Job Type
Full-time
Career Level
Mid Level
Education Level
No Education Listed