My expertise is in AI and product quality, building products that ✨work like magic✨. I'm super plugged into the AI community and latest tech/trends. I'm endlessly curious, product minded, and want to build products that win and stay winners. Talk to me about context engineering, LLM as a judge, or the future of Agents! 🤖
Outside of work, I'm all about singing+guitar/piano 🎶🎸, DJing house at parties 🎧, double black skiing ⛷️, wilderness photography 🌄, and fashion 👠.
August 2021 - Present
- Tech Lead on Agents Quality: Built AI stack for the initial product. Now we incorporate AI in new ways (following technology trends) to increase growth + hill climb on LLM judge metrics.
- Doc Q&A + Context Selection: Area owner for (built + scaling) the primary tools that fetch/manipulate/return doc context (RAG sidekick) in all our LLM-powered use cases.
- Core Assistant Quality contributor: Built many new features + guided product / quality decisions all around the Agentic and pre-Agentic engines of our famous Glean Assistant.
- Query Understanding: Developed early query parsing systems, spellcheck (15,000 triggers/day), acronym glossary (10,000 triggers/day)
- [Patented] Expert Detection: System to determine who knows the most about any given topic/area. Core component in Glean's Knowledge Graph.
June 2020 - September 2020
Deep Learning—Diagnosed data sampling processes and implemented new techniques to improve performance of the SOTA stack, e.g. sharding, upsampling on low resourced classes, etc.. Refactored and maintained eval pipelines to increase their throughput and efficiency.
June 2019 - September 2019
Autonomous vehicles. Bonus: Our team won the hackathon with a road quality monitoring/mapping system.
June 2018 - August 2018
Worked on Zero-Shot Multilingual Neural Machine Translation under Professor Rico Sennrich, and designed a discriminator that used an adversarial objective to universalize language representations during training.
June 2017 - September 2017
Computer vision and object detection. Trained deep learning models from scratch to build gun detection capabilities on mobile.
Let's get in touch.
Just shoot me an email,
or connect with me on LinkedIn.
San Francisco
(858) 380-9511
laurenzhu@alumni.stanford.edu