My Work
A selection of professional and research projects. None of these are coursework. For smaller projects and experiments, see my GitHub repositories.
Industry
Topaz Labs
ML Engineer · June 2024 – Present
At Topaz Labs I design, train, and deploy ML models for image and video enhancement used by millions of photographers and creators. My work spans the full pipeline from model architecture research to production serving infrastructure.
Autopilot
Built the flagship zero-click enhancement feature that automatically analyzes and enhances images without user configuration.
Portrait & Wildlife Models
Purpose-built enhancement models optimized for human faces and animal subjects with domain-specific training.
Auto Sharpen
API feature for intelligent sharpening that adapts to image content and degradation type.
Face Recovery V3 & High Fidelity V3
Advanced restoration models for recovering facial detail and preserving fine image structure.
Model Previews
Before/after comparisons from models I've built:
Auto Sharpen
View comparison →Auto Sharpen
View comparison →Wildlife Sharpen
View comparison →Sharpen & Denoise
View comparison →GAN Architecture Research
Led new GAN architecture research alongside a Research Scientist, producing our first whole-image conditioning model. This architecture enables globally-aware processing that wasn't possible with prior tile-based approaches.
Whole-Image Conditioning Architecture
Model(img, tile) → tile' — Cross-attention fuses global image semantics with per-tile features via an attention map, producing semantically-conditioned tile embeddings.
Detection & Semantic Models
Built detection and semantic understanding models used across the product pipeline for content-aware processing, quality assessment, and segmentation.
Model Serving
Optimized runtimes for hundreds of models being served in production, improving inference latency and throughput across the platform.
Hirebase
Co-Founder & CTO · November 2023 – Present
Hirebase is an AI-powered job search engine scanning 4M+ live jobs in real-time directly from company career pages. Serving 150+ customers worldwide at $80K ARR. I built the core tech platform from the ground up.
Core Ingestion Engine
Scaled from 1M to 10M+ records per month, scanning company career pages directly for real-time job data.
Token Parsing Models
ML models that extract structured data fields from raw, unstructured HTML strings on career pages.
Enterprise API
Massive data exports and a secure resume embeddings API with data privacy controls for enterprise clients.
Recommendation & Prediction
User recommendation systems and prediction models operating on unstructured job market data.
Model Inference Platform
Designed the core model inference platform powering all ML features: vector search for job matching, content classification, and structured extraction at scale.
Research
RPAL: Advanced Object Manipulation with the Barrett Hand
Research Scientist · USF Robot Perception and Action Lab
Research focused on enhancing robotic object manipulation through advanced representation learning. The goal: achieve precise control in tasks such as controlled object dropping using the Barrett Hand robot.
Multi-Objective Representation Learning
Encoder: State Representation
Transformer-based architecture processing tactile data, images, torque measurements, and joint angles. Trained with temporal, spatial, value, and state reconstruction objectives to create a linear learned representation.
Dynamix: Forward Dynamics Prediction
Predicts future states from current state embeddings and actions via a Delta Network and Predictor, enabling multi-step trajectory prediction in embedding space.
Critiq: Inverse Dynamics & Reward Prediction
Estimates actions and rewards from state transitions. Complements Dynamix through inverse dynamics learning with a time estimator for temporal context.
The shared encoder ensures consistent state representation across forward and inverse dynamics, creating a versatile foundation for advanced manipulation tasks.
Teach-a-Bull (IEEE AI Group)
Project Lead · USF IEEE
An extension of LLMaAiT-BE: formalizing graph-based generations over long-form text documents. The system uses LLMs in complex state-based environments modeled as MDPs, producing higher-quality generation than one-shot prompting for books, lectures, papers, and more.
Also proposed a distribution recreation hypothesis for assessing generation quality: if the generated document is semantically contained within the span of expert-generated documents, the generation is considered successful.
Personal & Open Source
MicrogradPlus
Auto-differentiation computational graph library extended from Andrej Karpathy's Micrograd. Extends scalar differentiation to support vector operations in a PyTorch-like style with n-dimensional tensors. Validated against PyTorch's auto-differentiation.
Reinforcement Learning in Chess
Applying reinforcement learning to chess using Monte Carlo Tree Search to approximate game state values. A neural network learns to emulate simulation values, with increasing reliance on state value predictions as the model improves. Inspired by DeepMind's AlphaGo and AlphaZero.
Gwen — Virtual Desktop Assistant
A voice-activated virtual assistant built in Python that controls and manages desktop environments. Features automated speech responses, wake-word activation, and integration with media platforms (Spotify, Netflix, YouTube). Includes an LLM backend server for conversation and chain-of-thought reasoning.
Robbie the DanciBULL Robot
USF HackaBull 2023
Built in 24 hours: a simulated robot that dances to any song. Uses policy and feature extraction networks to map audio data and joint angles to a probability distribution over 17 joints. Data pipeline constructed from Just Dance videos using a joint-angle extraction algorithm for offline RL, refined with RL-HF.
CoderSchoolAI
Open-source reinforcement learning library designed to make Agent AI accessible. Built in Python with PyTorch integration, providing neural network blocks, game environments, agent abstract classes, RL algorithms (DQN, PPO), and replay buffers. Used in both educational contexts and personal robotics research.
TerriBULL Robotics: BullBot
Robotics platform connecting the V5 Brain microcontroller with NVIDIA Jetson Nano for serial data communication and real-time object detection. Architecture includes a task manager for autonomous actions, mechanical system abstraction layers, and a decision model for path planning. ML research focused on offline and online RL (DDPG+HER) in simulated environments.
Astaria — 2D Action RPG
A 2D Action RPG built in the Godot engine featuring arcade mode with enemy waves, health potion drops, weapon upgrade systems, and hand-crafted pixel art. A solo project exploring game development and design.