
Senior Machine Learning Engineer at Robinhood
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Carnegie Mellon University's College of Engineering
Master's degree, Information Technology
January 1, 2014 – January 1, 2015
Pitzer College
Bachelor of Arts (B.A.), Computer Science
January 1, 2010 – January 1, 2014
Robinhood
Senior Machine Learning Engineer
April 1, 2021 – Present
Amazon Web Services
Software Development Engineer II
May 1, 2018 – April 1, 2021
East Palo Alto, CA
Parallel Machines
Machine Learning Software Engineer
June 1, 2017 – May 1, 2018
Sunnyvale, CA
Kaggle
Competitions Expert
January 1, 2017 – June 1, 2019
https://www.kaggle.com/cpruce
Juniper Networks
Software Engineer II
March 1, 2016 – June 1, 2017
Sunnyvale, CA
SLAC National Accelerator Laboratory
Practicum Student
August 1, 2015 – December 1, 2015
Menlo Park, CA-Mountain View, CA
Carnegie Mellon University
Graduate Teaching Assistant
August 1, 2015 – December 1, 2015
Hewlett-Packard
Software Engineer Internship
June 1, 2015 – August 1, 2015
Palo Alto, CA
New York Institute of Technology
REU Fellow
June 1, 2013 – August 1, 2013
Greater New York City Area
Pomona College
Mentor/Grader
January 1, 2013 – May 1, 2013
Claremont, CA
Mobile Mask R-CNN
December 1, 2017 – December 1, 2018
+ Worked in a team to convert the Keras/Tensorflow Mask RCNN’s Detection Layer to Tensorflow operations for cross-environment serializability. + Debugged aforementioned Mask RCNN model to be compatible with Tensorflow Mobile, extracted Tensorflow Protobuf model, and successfully exported more operations to the built libtensorflow_inference.so library. Wrote initial inference interface that accurately deciphers predictions from an architecture with 2 inputs, 5 outputs, and 2 parallel networks. + Replaced the Feature Pyramid Network’s ResNet50 backbone with MobileNetV1 for better performance on embedded devices, reducing inference time to 62% of the original speed.
Planet: Understanding the Amazon from Space (Kaggle competition)
April 1, 2017 – June 1, 2017
Created the 9th place (of 939 teams) solution for the "Planet: Understanding the Amazon from Space" Kaggle competition using convolutional neural networks, boosted random forests, and weighted-voting ensembles of submissions. Goal was to automatically label satellite images of the Amazon rain-forest, where labels assigned to an image ranged from 1 to 17 classes (agriculture, primary rain-forest, water, etc.). Used Pytorch, Keras, XGBoost, and Scikit-Learn/OpenCV2 for our solution. Pretrained models leveraged were Resnet[18, 34, 50], Densenet[121, 169, 201], VGG[16, 19], and Inception[V3, V4].
CVE-2016-3897
November 1, 2015 – December 1, 2015
The WifiEnterpriseConfig class in net/wifi/WifiEnterpriseConfig.java in Wi-Fi in Android 4.x before 4.4.4, 5.0.x before 5.0.2, 5.1.x before 5.1.1, and 6.x before 2016-09-01 includes a password in the return value of a toString method call, which allows attackers to obtain sensitive information via a crafted application, aka internal bug 25624963. Rewarded by Google for Medium-level zero-day exploit.
Cookie Manager
July 1, 2015 – August 1, 2015
Developed a cookie manager Chrome extension that allows filtering based on time and domain as well as access and deletion.
Reverse Engineering: Malware Analysis
January 1, 2015 – May 1, 2015
Investigated and wrote real samples of malware using tools and methods taught from a CERT professional. • Discovered and analyzed most components of the bank trojan Neverquest • Documented unpacking, obfuscation techniques, and C&C communication • Used IDA Pro, OllyDbg, OllyDump plugin, and Import Table Reconstructor • Assignments included IDC scripting and uncovering malware driver/device objects amd IRP hooks in kernel debugging with WinDbg
GMPLS Simulation
December 1, 2014 – January 1, 2015
Construction of routing tables and bi-directional GMPLS tunnel over packet-switching capable (PSC) routers and light-switching capable (LSC) routers.
Tor Analyzer
November 1, 2014 – December 1, 2014
Features include observing IP addresses, country codes, bandwidths of relays in established Tor circuits, and seeing which countries block a particular site.
Twitter Analytics
October 1, 2014 – November 1, 2014
Designed and implemented a web service that uses REST interface to respond to queries on a large twitter data-set (1 TB) which has been transformed and loaded into a database. • Hosted the web service on Amazon EC2 instances behind an Elastic Load Balancer • Designed an efficient Extract, Transform and Load (ETL) process to convert the given dataset (JSON) to comma separated values that can be imported into the backend database • Ran the ETL using Elastic MapReduce offered by Amazon Web Services • Selected MySQL as the backend database after comparing its performance with HBase for the given queries • Scaled the MySQL backend using horizontal replication. (The queries were read-only) • Team size: 3 students
Tiny Shell
August 1, 2014 – September 1, 2014
A simple shell that executes particular user input, runs foreground and background processes, handles signals, redirects I/O, and reaps zombie children processes.
Fault Tolerant Distributed Key-Value Store
April 1, 2014 – May 1, 2014
Distributed key-value storage system that uses unique identifiers to store and retrieve data disbursed among the nodes that hold backups of neighbors in its chord and monitors for failure.
Cultural Fit Analysis
The candidate demonstrates a strong cultural fit for a dynamic, innovation-driven environment. Their extensive involvement in Kaggle competitions showcases a passion for continuous learning, pushing boundaries, and achieving top-tier results. The diversity of personal projects, from Chrome extensions to malware analysis, indicates intellectual curiosity and a broad technical interest beyond core ML, which can foster cross-functional collaboration. Their experience at AWS and Robinhood, combined with leading teams, suggests an ability to thrive in fast-paced, high-impact settings. The academic background from Carnegie Mellon further reinforces a strong foundation and commitment to excellence.
Soft Skills & Operational Fit
The candidate's project descriptions and professional experience highlight strong problem-solving abilities, a proactive approach to identifying and resolving technical challenges (e.g., StyleGAN AdaIN issue, bug team-assignment automation), and a collaborative spirit (team projects, leading teams). Their Kaggle competition success also indicates a high degree of self-motivation and continuous learning. The breadth of projects suggests adaptability and a willingness to tackle diverse technical domains.