EMBEDDED AI
Real-Time IR Target Detection on Embedded Compute
Designing AI/ML perception for infrared imagery under strict latency, memory, and false-alarm constraints.
Computer VisionInfraredCNNsEmbedded AI
Engineering portfolio
Selected Projects
Case studies spanning AI/ML, autonomous perception, GN&C, simulation, computer vision, and AI-enabled engineering infrastructure.
ML SYSTEMS
Neural Architecture Search for Accuracy-Efficiency Tradeoffs
Using NAS to search CNN design space with deployment constraints in mind rather than optimizing accuracy in isolation.
NASPyTorchCNNsOptimization
EMBEDDED COMPUTE
Custom SIMD Inference Engine for Resource-Constrained Hardware
Reducing ML latency and memory use by treating inference as a data-movement and microkernel problem, not just a model problem.
SIMDC/C++InferencePerformance
AUTONOMY RESEARCH
Safe Multi-UAV Coordination with Deep Reinforcement Learning
Doctoral research on decentralized multi-agent coordination under partial observability and explicit safety / temporal-spatial constraints.
Ph.D. Computer Engineering
MARL decentralized coordination
Reinforcement LearningMulti-Agent SystemsUAVsSafety
ML INFRASTRUCTURE
Flight-Test MLOps and Data Pipeline
Turning fragmented test imagery into a repeatable, traceable ML data path for faster preprocessing, training, deployment, and engineering analysis.
MLOpsETLData EngineeringPython
GN&C SYSTEMS
6-DOF Simulation, Digital Twins, and Monte Carlo Automation
Building simulation and DevOps infrastructure to evaluate dynamic-system performance, detect defects earlier, and automate repeatable release analysis.
6-DOF dynamic simulation
CI/CD automated analysis
GN&CSimulationDigital TwinMonte Carlo
TINYML
TinyML and Embedded Sensor-System Prototyping
Deploying ML models to Cortex-class processors while building the surrounding embedded software, sensor stack, and real-time automation infrastructure.
Cortex-A5 embedded ML target
Cortex-M4 microcontroller target
TinyMLTensorFlow LiteCortex-MRTOS