Build the models and agents that read a plant's records and connect them, so scientists and engineers get answers they can check against the sources.Katalyze reads the records a medicine is made from: batch records, certificates of analysis, deviation records and the data around them. Much of it arrives as scanned pages, forms and tables. The models you build turn those pages into data the Context Layer can connect, and the agents on top of it retrieve, reason over and cite that material.You'll also build the evaluations that tell us whether an answer is right before an expert sees it, working with domain experts to define what correct looks like. You'll own systems from prototype to production.You'll work with the AI team and with deployment, close to the scientists and engineers who use what you ship.



The role is based in our Current York City office.What you'll do Train and evaluate models that read scanned and digital manufacturing recordsBuild the pipelines that turn each read into structured data with its sourceMeasure accuracy on real documents and close the gaps you findWork with deployment on the records each customer bringsDesign agent workflows that retrieve, reason over and cite records across systemsBuild evaluation sets with domain experts and run them on every model changeImprove accuracy, latency and cost, and mentor engineers on the AI teamWhat we look for Five or more years building machine learning systems in productionExperience with document understanding, OCR or language modelsStrong Python, and the habit of measuring before changingExperience building retrieval systems and evaluation frameworks for LLM-based productsA record of taking models from prototype to production and keeping them reliableClear writing about trade-offs and care for the people who rely on the answersNice to have Experience in life sciences or another regulated industryPublished work in document AI or information extractionExperience deploying models in on-premises or validated environmentsKatalyze is an equal opportunity employer.#J-18808-Ljbffr

📌 Senior Machine Learning Engineer (Toronto)
🏢 Bonfirevc
📍 Toronto