RODERICK L. RENWICK

Machine Learning Engineer | Computer Vision Specialist

📍 Bloomfield Hills, MI • rodericklrenwick@gmail.com • (248) 914-0569 • rodericklrenwick.com • github.com/RLR-GitHub

~/profile$ cat summary.txt

Machine Learning Engineer with expertise in computer vision systems, from rapid prototyping to embedded deployment. Experienced in building real-time inference pipelines, sensor fusion architectures, and hardware-software co-design for robotics and autonomous systems. Strong foundation in end-to-end implementation across research, development, and deployment phases.

~/career$ ls -l experience/

Machine Learning Research Intern @ Raytheon Technologies Research Center

INDUSTRY

📅 Summer 2023 📍 East Hartford, CT 🏢 Robotics Intelligence Division

Developed rapid prototyping and data collection methods for robotics intelligence applications
Enabled smart detection of metal anomalies using structured light and ML-based inspection algorithms
Built real-time inference pipelines for embedded GPU platforms, optimizing for latency and throughput
Earned commendation from leadership for innovative ML solutions addressing complex operational requirements

Research Assistant — MDAS.ai Autonomous Shuttle @ University of Michigan

RESEARCH

📅 Summer 2018 – Winter 2020 📍 Dearborn, MI 🏢 Autonomous Vehicle Project

Core team member for MDAS.ai autonomous shuttle development, contributing to perception and sensor systems
Designed sensory data pipeline on NVIDIA Jetson TX2 for real-time multi-sensor processing
Implemented real-time object detection achieving 30fps on embedded hardware using YOLO architecture
Developed LiDAR–camera calibration pipeline for robust sensor fusion in autonomous navigation

Engineering Intern @ Ford Motor Company

INDUSTRY

📅 Summer 2017 📍 Dearborn, MI 🏢 Battery Electric Vehicle Division

Gained expertise in functional safety standards (ISO 26262) for automotive systems
Developed logic tracing tools for safety-critical software analysis and verification
Documented FMEA analysis for high-voltage safety circuits in powertrain systems

~/projects$ find . -type f -name "*.py"

Smart Cat Door System (CatNet 2.0) CV

./catnet_embedded_cv.py

Built complete access control system using computer vision for pet identification. Implemented UNet for semantic segmentation and custom CNNs for robust animal classification. Deployed on embedded hardware with real-time inference.

Deep-Fake Cat Generator (WGAN-GP) GAN

./wgan_gp_generator.py

Evolved architecture from standard GANs to WGAN-GP for high-fidelity image synthesis with training stability. Analyzed generator-critic optimization dynamics; debugged mode collapse and convergence issues.

ParkSmart iPhone Application iOS

./parksmart_cv.py

Developed parking management system integrating real-time CV analysis with native iOS application. Applied homography matrices and perspective transforms for accurate parking space detection.

VHDL Perceptron Implementation FPGA

./fpga_mlp_accelerator.vhdl

Translated Python MLP to optimized VHDL for FPGA deployment, demonstrating hardware-accelerated neural networks. Focused on combinational logic reduction and resource optimization.

~$ cat skills.json

machine_learning:

PyTorch TensorFlow JAX scikit-learn Hugging Face

computer_vision:

OpenCV YOLO Detectron2 MediaPipe TensorRT

hardware_embedded:

FPGA/VHDL NVIDIA Jetson CUDA ARM Cortex RISC-V

languages:

Python C++ C Java Assembly VHDL SystemVerilog

tools_platforms:

Linux Git Docker AWS ROS/ROS2 Vivado

domains:

Robotics Autonomous Systems Edge AI Safety-Critical Software

~$ cat education.log

M.S. Electrical & Computer Engineering — Purdue University

February 2026

Focus: Signal & Image Processing, Deep Learning, Computer Vision

B.S. Computer Engineering (with Distinction) — University of Michigan-Dearborn

Winter 2020

Focus: VLSI Design, Embedded Systems, Autonomous Vehicle Perception

~$ cat research_interests.txt

Real-Time Inference & Edge AI Computer Vision Systems Hardware-Software Co-Design Autonomous Systems Perception Sensor Fusion Architectures Embedded ML Deployment Generative Model Stability FPGA/Edge TPU Acceleration