Work experience

Sunkist Growers

Software Engineer II

• Designed and implemented new defect and decay detection algorithms in C++ and Python using traditional computer vision (CV) and machine learning-enabled CV

• Integrated new technologies with pre-existing architecture (added ZeroMQ for inter- and intra-system communication, ONNX for machine learning inference and model deployment)

• Developed and deployed new asynchronous data capture functionality for in-house data annotation tool

• Prototyped CV-based machine learning algorithms for new fruit defect detection with OpenCV, Tensorflow, PyTorch, and Scikit-Learn in Python

• Regularly dialogued with end-customers, regional service partners, and in-house service team to discuss software improvements 

• Modernized aging software written in C with new C++17 functionalities 

• Spearheaded Git migration from Team Foundation Version Control and developed CI/CD pipeline for Azure DevOps repositories

Falcon ExoDynamics

Software/Firmware Engineer

• Architected multithreaded software design and developed C++ software payload for space domain awareness (SDA) software on traditional desktop environments (Ubuntu Linux) and embedded environments (Xilinx ZYNQ Ultrascale+ with embedded Linux), with four completed releases to customer

• Developed sensor control interfaces for laser rangefinder, long-wave infrared (LWIR) cameras, and visible-spectrum cameras (UART and TCP/IP)

• Integrated sensor and electromechanical actuators using C++ and Python for prototype lunar landing payload in response to NASA TechLeap competition (LITTLE OWL)

• Performed data analysis and field testing of illumination solution for LITTLE OWL to aid in proposal writing and early prototyping 

• Wrote in-house proposal for next-generation, low-SWaP-C hyper-spectral star tracker for small satellites

• Designed and maintained CI/CD pipelines for internal GitLab repositories, including Docker container creation/maintenance and static application security testing (SAST) for both C++ and Python (using Flawfinder and Bandit)

June 2018 - July 2019

UCR Embedded Systems Lab 

Undergraduate Researcher

• Developed configurable components for a paper microfluidics computer-aided design (CAD) framework, specifically a paper-based analytical device (µPAD)

• Conducted quality assurance testing for newly-designed components to ensure compatibility with previous components and user-friendliness

• Assisted in lab trials to determine fluidic limits of new paper microfluidics devices across multiple ink colors and border thicknesses.