people talk about “ai in healthcare” as if it’s a slogan. the real work is getting models to beha...people talk about “ai in healthcare” as if it’s a slogan. the real work is getting models to beha...
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Federico's avatar
Federico Imparatta
• Dec 7
people talk about “ai in healthcare” as if it’s a slogan. the real work is getting models to behave in the real world, with messy data, uneven labeling, and edge cases that don’t care about your roadmap.
at ataraxy, i led the machine-learning stream for a large clinical data product. we rebuilt the entire pipeline: data normalization, feature extraction, model training, evaluation, and deployment. we dealt with inconsistent medical records, contradictory annotations, shifting taxonomies, and the usual parade of surprises you only find once you start training at scale.
we added explainability, tightened feedback loops with domain experts, and set up the automation so retraining didn’t depend on heroics. the result was a model that performed well, generalized beyond the sandbox, and actually shipped.
AI Agent EngineerProject ManagementProduct ManagementGoogle GeminiJiraOpenAI
Back to feed
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started