Menu

hey there

👋 I'm Lauren Zhu.

About

More About Me

I graduated from Stanford in 2020 with my BS and MS in Computer Science, with a focus in AI. I'm all about building impactful AI applications, empowering women in tech, singing and guitar, skiing, wilderness photography, and fashion.

My Work Experience.

August 2021 - Present

Glean

Senior Software Engineer

- Tech Lead on Agents Quality: We built the initial product, and continue to hill climb on LLM judge metrics and incorporate new AI-powered features to keep it cutting edge.
- Assistant Quality: Built new features and use cases all around the Agentic (and pre-Agentic) engines of our famous Glean Assistant.
- Doc Q&A: Area owner for (built + scaled) the primary tool that reads doc contents in LLM-powered products.
- Query Understanding: Developed early query parsing systems, spellcheck, acronym expansion, etc.
- [Patented]: Expert detection—system to determine who knows the most about any given topic/area.

June 2020 - September 2020

Apple Special Projects Group

Machine Learning Intern

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

Ford Greenfield Labs

Machine Learning Intern

Autonomous vehicles. Bonus: Our team won the hackathon with a road quality monitoring/mapping system.

June 2018 - August 2018

University of Edinburgh

AI Researcher (NLP)

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

Qualcomm

Software Engineering Intern

Computer vision and object detection. Trained deep learning models from scratch to build gun detection capabilities on mobile.

Things that Shape Me

Author image
Stanford Jump Rope Team

I've been performing and competing with the Stanford Jump Rope team since my earliest days at Stanford. We do crazy flips and stunts, dance in double dutch, and jump on our butts!

Author image
Stanford Women in Computer Science

This community has shaped my journey at Stanford both personally and professionally. As the Co-President my junior year, I had the honor of working with hundreds of women in CS that I admired.

Author image
Wilderness photography

When I'm out in wild landscapes, I'm home. When the breeze grazes my cheeks, when the pine needles whistle above, when the water rumbles below. To capture the sublimity of nature is to inspire awe, to preserve the land.

Author image
Recording Covers

During quarantine, I picked up the guitar to sing with and haven't put it down since. If I'm not working or hiking, odds are I'm learning the fingerstyle to a new song. Annie's song. Landslide. Cherry Wine.

Author image
Searing Steaks

I grew up around Chinese food, but spent countless hours soaking up culinary knowledge from The Food Network. I find cooking to be a form of art, and love to apply my creativity to classic dishes and make them my own.

Author image
Piano

While my competition days are behind me, nothing beats the expression that Liszt, Chopin, and Debussy had intended for their music. That these pieces retain their beauty and power for hundreds of years is a marvel.

Author image
Travel

I am forever grateful for the opportunity to travel. To be a part of cultures that are not my own, places that I did not know, beauty I cannot comprehend. These experiences make for insane stories. These are the lessons extend beyond the classroom.

Portfolio

See My Latest Work.

Dive deep into my work, both professional and personal.

Recolorizing B&W Images

Computer Vision

Hinge Loss on CNNs to recolorize black and white landscape images.

AI Travel Itinerary Planning

Ant Colony Optimization

Ongoing project by Peggy and me! :)

Pixel 4 Pixel

Human Computer Interaction

In a collaboration with the Stanford HCI group on a project to build a digital self-tracking took, I implemented a grid detection algorithm using computer vision to extract colors from a hand-drawn grid.

University of Edinburgh

Neural Machine Translation

NLP research conducted at the University of Edinburgh under Professor Rico Sennrich.
Adversarial Training in Zero-Shot Multilingual Neural Machine Translation.

Question and Answering

Deep NLP

Extending Answer Prediction for Deep Bi-directional Transformers.

MAXQ: Autonomous Rockets

Reinforcement Learning

This paper aims to solve both a hierarchical reinforcement learning task and a collision avoidance problem for an autonomous rocket in a field of asteroids. This problem is modeled as a Markov decision process and uses the MAXQ decomposition and MAXQ-0 learning algorithm which are compared against Flat Q-learning.

Rendering a Scene

Computer Graphics

Testing my abilities as an interior designer and computer graphics engineer,
my partner and I created and rendered this scene using a Ray Tracer and Blender.

AXLES

BMW Collaboration

Senior project capstone, software project with BMW combining micro-gesture recognition and gaze tracking into an interesting use case for an autonomous vehicle. See Github wiki link for more information.

Augmenting Deep Speech Recognition

Spoken Language Processing

We mitigate state-of-the-art models' tendencies to overfit by using a combination of augmentation techniques—making pitch, amplitude, noise, and vocal tract length perturbations, as well as time and frequency masking. All our experiments outperform the baseline in multiple speech recognition metrics.

Reconstructing Paintings

Computer Vision

Preserving art is a test of time—often there are damaged/missing portions. With no references to how the painting was at its peak of creation, there lies a problem in creating truthful reconstructions of unique, rare art pieces. Utilizing Model Agnostic Meta Learning (MAML)on top of a CNN, we develop a regeneration model that accurately restores paintings, generalized across varying artistic complexity.

Context Graph Generator

Knowledge Graphs

Get this—55% of users read online articles for less than 15 seconds. The general problem of understanding large spans of content is painstaking, with no efficient solution. We create a tool that generates analytical, concept graphs over text, providing the first-ever standardized, structured, and interpretable medium to understand and draw connections from large spans of content.

Vlog

Stanford @ Cinque Terre

Music

Coffee with Charlie

Cinematography

Central Coast of California

23

🏞️ National Parks Visited

2555

☕ Cups of Coffee

110

🚀 Projects Completed

570

🤗 Hugs Given

Contact

Say Hello!

Let's get in touch.
Just shoot me an email,
or connect with me on LinkedIn.

Location

San Francisco

Phone

(858) 380-9511

Email

laurenzhu@alumni.stanford.edu