👩🏽💻 About Me
Welcome! I'm Shreya Shankar. I am completing my PhD in database management systems with a human-centered focus. I study machine learning (ML) and artificial intelligence (AI) engineers and how to build better tools for them. I am fortunate to be advised by Dr. Aditya Parameswaran at UC Berkeley. Go Bears! 🐻
Prior to my PhD, I was the first ML engineer at Viaduct, did research engineering at Google Brain, and software engineering at Facebook. Before all of that, I did my BS and MS in computer science at Stanford. Go Trees! 🌲
My work broadly focuses on enabling successful deployments of AI systems and empowering non-engineers to build AI systems. I'm working on the following projects:
Data Management Systems
- A framework to build LLM pipelines with self-updating prompts
- Automatically synthesizing assertions for LLM pipelines
- Large-scale data processing (e.g., sorting, rating, labeling) with LLMs
- Real-time, approximate monitoring of ML pipeline performance with feedback delays
- Interfaces for helping LLM pipeline developers write assertions and evaluations
- Low-code tools to build LLM workflows with self-updating prompts
If you are interested in working on any of these projects or collaborating, please contact me via email. I am open to undergrads who have taken a databases course and/or a graduate level machine learning course. If you go to UC Berkeley, please mention that in your email. I apologize if I am unable to respond to your email in a timely manner.
To reach me, you can email firstname.lastname@example.org. I am also on Twitter and Github.
My (typically-outdated) CV is available for download here.