AI-powered pathology platform for cancer diagnosis and treatment optimization
PathAI operates a machine-learning platform purpose-built for digital pathology, running on a modern data stack (Python, PyTorch, TensorFlow, Kafka, Snowflake, dbt, Airflow) scaled across AWS and Kubernetes. The engineering-heavy hiring profile, combined with active projects spanning model deployments, MLOps, and clinical trial infrastructure, reveals a company transitioning from research-stage AI into production clinical workflows—a shift reflected in concurrent pain points around scaling ML infrastructure, bridging the research-to-production gap, and optimizing storage for experiment data.
PathAI develops an AI platform for pathology that improves diagnostic accuracy and treatment efficacy in oncology and related diseases. The product sits at the intersection of clinical diagnostics and machine learning, serving hospital systems, biopharma companies, and diagnostic laboratories. The company combines a research-oriented project portfolio (exploratory biomarker studies, clinical trial integration) with infrastructure-heavy engineering (ETL modernization, MLOps tooling, database-backed ML applications), operating from Boston with a 501–1,000-person team distributed across the United States, Bulgaria, the United Kingdom, and Brazil.
Python, PyTorch, TensorFlow, FastAPI, Django, PostgreSQL, Kafka, RabbitMQ, Snowflake, dbt, Apache Airflow, Spark, Docker, Kubernetes, AWS (EKS, RDS, SQS, MSK), GitLab CI/CD, Prometheus, Grafana, and Datadog.
PathAI actively recruits in the United States, Bulgaria, the United Kingdom, and Brazil.
Other companies in the same industry, closest in size