MLE with ~10 years building high-impact recommendation systems at Spotify, Meta & LinkedIn
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Machine Learning Engineer with nearly 10 years of experience specializing in the end-to-end design, development, and deployment of large-scale recommendation systems. Proven track record of delivering significant metric improvements at industry leaders including Spotify, Meta, and LinkedIn. Expertise in deep learning architectures (Two-Tower, Transformers), candidate retrieval, ranking models, generative model, and scalable MLOps infrastructure for systems serving billions of users.
The University of Texas at Arlington
Doctor of Arts, machine learning and computer vision
N/A – Present
Faire
Machine Learning Engineer
January 1, 2026 – Present
Spotify
Machine Learning Engineer
November 1, 2022 – January 1, 2026
Hybrid
Machine Learning Engineer
January 1, 2021 – January 1, 2022
Machine Learning Engineer
January 1, 2017 – January 1, 2021
Cardlytics
Software Engineer
January 1, 2015 – January 1, 2017
Atlanta Metropolitan Area
Hand Shape Registeration
January 1, 2013 – June 1, 2013
Designed a method to detect the hand and its associated fingers using graphical probabilistic model (modified HMM). The main goal is to achieve real-time performance despite the computational complexity of using graphical model.
Object Detection
September 1, 2012 – May 1, 2015
- Designed a hand detection algorithm for American Sign Language sign videos based on random forest algorithm - The proposed hand detector achieved an accuracy of 89.3% for 1-handed signs and 86.2% for 2-handed signs which is far better than other state-of-art object detection methods - Implemented Viola-Jones object detection framework using Python for face detection - Python was used for implementing random forest and annotation GUIs were written by Matlab
ASL Sign Ranking
August 1, 2011 – Present
-Replaced the DTW-based similarity measure in the ASL dictionary search system with BoostMap which is an efficient method to obtain rankings of all database sign videos in approximate order of similarity to the query sign -BoostMap made the system about 3 times faster, with negligible losses in accuracy -C++ was used to implement the idea
Human Action Mining
June 1, 2011 – May 1, 2015
- Designed a human action mining algorithm which could discriminate falls from other actions using Kinect depth camera, C++ and MS Kinect SDK - Introduced an algorithm to calculate the person’s height using Kinect depth camera - proposed several discriminative features for describing fall action and employed a Naive Bayesian Classifier to combine these features
American Sign Language (ASL) Dictionary Search
August 1, 2009 – Present
-Designed an ASL sign search engine. The user submits as query a video of the sign of interest to the system. The system then searches a large database of sign videos in order to find the best matches for the query video. -In user-independent experiments, with a system vocabulary of 1,113 signs, the correct sign was included in the top 10 matches for 78% of the test queries. -Developed feature extraction and large-scale multiclass classification modules using C++, Adaboost, Dynamic Time Warping algorithm (DTW) and HOG descriptor.
Forest Fire Monitoring System
September 1, 2007 – June 1, 2009
- Designed and implemented a fire monitoring system that can help prevent forest fire using C++ - This system is currently monitoring several forests in China. - The core part of this system is a forest fire alarm algorithm which is based on SVM
Neural Networks and Deep Learning
Coursera
June 24, 2026 – Present
Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization
Coursera
June 24, 2026 – Present
Cultural Fit Analysis
The candidate's experience at Spotify, Facebook, and LinkedIn, all known for their data-driven and innovative cultures, suggests a strong cultural fit for similar fast-paced, tech-forward environments. The diversity of projects, from academic computer vision to large-scale recommendation systems, indicates adaptability and a broad interest in ML applications. The open-source contribution (Feathr) also points to a collaborative mindset. The target role of ML Engineer aligns perfectly with their career trajectory and expertise.
Soft Skills & Operational Fit
The candidate's experience descriptions highlight leadership in major initiatives, architectural contributions, and a focus on reducing development lifecycles, suggesting strong problem-solving, innovation, and operational efficiency. The consistent progression in high-impact roles at leading companies indicates a strong work ethic and ability to thrive in demanding environments. The detailed project descriptions, even for personal projects, suggest good communication of technical concepts.