Natural Language Processing & Machine Intelligence

Between mid-2017 to mid-2020, I worked as a Senior Staff Data Scientist at Primer AI located in San Francisco, CA. I worked on developing complex, scalable, multilingual natural language processing (NLP) pipelines that utilize the state-of-the-art NLP algorithms and machine-learning models.

Work at Primer

Primer builds machines that can read and write like a human. We focus on automating the analysis of enormous document sets to help business clients understand both the big picture and evidence behind it.

My work at Primer includes performing advanced time series analysis to identify trends and tell stories; parsing and classifying large amount of unstructured text data such as news articles, financial reports, and scientific papers; developing scalable clustering and event detection systems that can process hundreds of millions of documents; information and knowledge extraction and aggregation from unstructured sources. I enjoy being involved in the process from pretotyping to production.

During my time at Primer, I spent a lot of effort designing, building, and maintaining scalable and high-performance natural language processing pipelines. Some of these were discussed in my talk at the Ray summit connect event.

You can learn more about Primer from the company website and our tech blog. Also, you can find some news articles about Primer on Fortune, TechCrunch, Wired, and DCVC blog. We also launched a publicly available COVID-19 Primer website, which I helped build, to help researchers and journalists better understand the pandemic.