ML and simulation platform for computational drug discovery
Deep Origin built a full-stack computational platform for drug discovery using Node.js, TypeScript, Python, and PyTorch on Kubernetes — a tech composition optimized for both web services and large-scale ML model training. The hiring profile (senior engineers and design leads, active roles in ML infrastructure and developer tooling) and project backlog (large-scale biological models, benchmark systems, test automation) reveal a company scaling from MVP toward production ML ops. Pain points around low-data ML regimes and model evaluation benchmarks suggest they're solving hard ML problems in biology where traditional training datasets don't exist.
Deep Origin builds computational tools for drug discovery, targeting research scientists and biotech teams working on early-stage drug development. The platform combines bioinformatics tooling with ML simulation capabilities to compress R&D timelines. Founded in 2022, the company operates from South San Francisco with 51–200 employees. They're actively hiring across engineering, design, and research roles in the United States and Armenia, with a leadership-heavy seniority mix indicating investment in technical depth and operational scaling.
Deep Origin runs on Node.js, TypeScript, Python, PostgreSQL, MongoDB, Kubernetes, and PyTorch. Frontend is React. They use Playwright and Cypress for test automation, Docker for containerization, and Prometheus/Grafana for monitoring.
Their active projects include large-scale ML models for biological systems, robust data processing pipelines, benchmark development for model evaluation, end-to-end test automation, internal developer tooling, and monitoring systems.
Other companies in the same industry, closest in size