Laleh Soltan Ghoraie
About
Laleh Soltan Ghoraie is from San Francisco Bay Area. Laleh Soltan works in the following industries: "Computer Software", "Internet", "Banking", "Research", and "Hospital & Health Care". Laleh Soltan is currently Sr. Machine Learning Engineer at Twitter, located in San Francisco Bay Area. In Laleh Soltan's previous role as a Sr. Data Scientist at RBC, Laleh Soltan worked in Toronto, Canada Area until Aug 2020. Prior to joining RBC, Laleh Soltan was a Machine Learning Researcher at Borealis AI (Royal Bank of Canada) and held the position of Machine Learning Researcher at Toronto, Canada Area. Prior to that, Laleh Soltan was a Postgraduate Affiliate at Vector Institute, based in MaRS Centre, West Tower 661 University Ave., Suite 710 Toronto, ON M5G 1M1 from Feb 2018 to Feb 2019. Laleh Soltan started working as Scientific Associate, Machine Learning at University Health Network in Toronto, Canada Area in Jan 2017. From Oct 2015 to Dec 2016, Laleh Soltan was Postdoctoral Researcher at University Health Network, based in Toronto, Canada Area.
If you’re looking for Laleh Soltan Ghoraie's email address, you can find it on finalscout.com. Finalscout is a professional database with more than 500 million business professionals and 200 million company profiles.
Laleh Soltan Ghoraie's current jobs
Laleh Soltan Ghoraie's past jobs
I mainly focused on improving a pre-existing Natural Language Processing pipeline/product for finding the most semantically relevant policy/regulatory documents and classification of Form 10-Ks. Improvements involved: data collection and benchmarking existing and developing pipelines, prototyping new pipelines using state-of-the-art of contextual text representation techniques, and productionization of the new pipelines.
My main research interest was Pharmacogenomics, and I successfully applied statistical methods on gene-expression profiles of drug-treated human cell lines for applications such as drug repurposing to treat Skin Fibrosis. Furthermore, I built several predictive models using cancer patients' data such as imaging data.