Jan 2024 – Jan 2024 · 0 mo · New York City Metropolitan Area

• Led the migration of model inference from hosted on the external cloud service Modal to self-hosted Ray cluster running on Kubernetes to bring inference in-house for lower costs and optimized pipelines
• Set up tools and infrastructure to allow spinning up new models in hours
• Designed and generated Python and Typescript SDK to get models in the hands of customers within the day of the request
• Optimized various model inference with batching, vLLM and PyTorch, reducing latency of pipelines by up to 80%
• Led the setup of tracing by integrating OpenTelemetry with Jaeger and augmented Ray logs and Prometheus metrics to allow SDK developers to get features out in hours rather than days and help pinpoint bottlenecks in customers’ AI pipelines

Jan 2021 – Jan 2023 · 2 yrs

• As first backend hire, laid down the foundation of the company’s microservices through implementing the original services, setting up Kubernetes cluster with Helm and Terraform on EKS, and the CI/CD pipeline with Github Actions
• Architected and led the implementation of the Control Plane-Data Plane split utilizing Kubernetes Operator pattern to make the system declarative, resulting in the creation of the egress only Data Plane agents to be installed in customers’ VPC that are orchestrated by the hosted Control Plane, leading to significant reduction of deployment time from weeks to just hours

Jan 2019 – Jan 2021 · 2 yrs · Palo Alto

• maintain CLI for Confluent Cloud and Confluent Platform (on-prem)
• add observability to the CLI by integrating Segment Analytics to track user actions
• using the observability metrics and customer's feedback to improve user experience
• add automatic refreshing of authentication token, and support for JSON and YAML output to allow scripting of the CLI
• Implemented automated CLI binaries build, testing and release pipeline involving Goreleaser tool, bash script, GNU Make script, AWS S3 and Azure DevOps Pipelines
• Automated end-to-end cloud system test for Cloud CLI

Jan 2018 – Jan 2018 · 0 mo · UC Berkeley

• Taught two different lectures of five students weekly and hosted office hours
• Taught data structures using Java

Jan 2018 – Jan 2018 · 0 mo · Emeryville, California

• Designed automation tests, comparing server’s data with what is populated in the UI in various use cases
• Created user data logging system validation framework which structures the querying and managing of data for comparison between the logging system and the application server for all use cases

Jan 2017 – Jan 2018 · 1 yr · UC Berkeley

• Taught weekly lectures and hosted office hours
• Met weekly with other mentors to discuss teaching approaches
• Taught intro to CS using Python, and data structures using Java

Jan 2017 – Jan 2017 · 0 mo · Bangkok Metropolitan Area, Thailand

• Created a desktop application using MVC design pattern with python and PyQt, to collect various runtime data and display the data as tables and graphs where users can control what populates in columns and rows
• Added features requested by users to the company’s Camera and Object Motion Tracking software with python (for functionality) and FLTK (for UI)
• Adjusted methods & infrastructure of the company’s software in C++, python and SWIG to fix bugs

Jan 2015 – Jan 2016 · 1 yr · UCSD

• Analyzed research papers and equations on existing DPF machines and their design parameters
• Used MATLAB to create a simulator of design parameters to calibrate the design of the machine, then used AUTOCAD to create designs with the chosen parameters