- Building EVI (Empathic Voice Interface), an AI with emotional intelligence.

- AWS SageMaker Model Inference, a highly scalable platform for hosting ML models on the cloud, and serving predictions.- Inference response streaming: part of a 2 person engineering team to enable streaming inference responses from SageMaker endpoints. This allows pieces of the response to be returned to the client as soon as they become available, instead of waiting for the entire response to be generated. This is a critical feature for LLMs, and is used by AWS Bedrock as well as many external customers.- Multi-replica endpoints: worked on a feature that allows customers to deploy hundreds of foundation models on the same infrastructure. Models are optimally placed to maximize instance utilization, and scale independently according to demand. This leads to a significant reduction in deployment costs.- Load aware routing: led the API design for a feature that intelligently routes traffic to endpoint instances based off of a load heuristic. This has been shown to reduce e2e latency of LLM inference responses by more than 30%, and is currently being used in production by large customers.- Distributed graph inference: worked on a feature that allows customers to deploy a computation graph of logical nodes, where each node is a cluster of instances that auto-scales according to demand.- Region build automation: launched the SageMaker Inference platform in 4 new AWS regions, ap-southeast-3, me-central-1, us-gov-east-1, and ca-west-1. Helped automate the process, reducing the dev effort for launching future regions by more than 90%.- Helped maintain a large-scale distributed system with millions of TPS and a 99.9% availability SLA. Addressed root causes for platform issues, improved internal tooling, and answered customer questions.

- Research in efficient machine learning and computer vision (RISE Lab).- Worked on improving temporal consistency for depth estimation on monocular video.

- Helped facilitate the Innovation Catalysts program, which provides funding and mentorship to students pursuing innovative projects at the intersection of design and technology.- Mentored early stage projects ranging from educational tools to microrobotics for biological research.

- Research in robotics, control, and intelligent systems (HART Lab).- Programmed ROS nodes to extract and analyze point cloud data from a soft robotic sensor.- Used sensor information to control a KUKA robot to perform edge following tasks.

- Worked on AWS SageMaker Model Inference, a highly available, low latency service for hosting ML models and serving predictions.- Designed and implemented a new feature for AWS SageMaker Model Monitor that allows customers to detect outliers and distribution shift for computer vision models.

- Participated in the Fall 2020 HotDesk cohort.- Applied lean-startup principles to an early-stage accessibility startup.

- Split time between business operations and software development roles. Conducted user research and competitive analyses. Built new front-end features of a time tracking application, interfacing with back-end infrastructure and the existing code base.

- Worked with the director of OneProsper to launch a fundraiser that provided water storage systems for farmers in the Thar desert. The initiative raised money through a series of fundraising yoga and meditation workshops, and was hosted by a number of Bay Area schools and companies.