AI Systems Researcher • Embedded Architect • Infrastructure Strategist
🌐 Website • 📖 Scholar • ✍️ Medium • 🎙️ Podcast
-
AI Systems
Latency reduction, deployment architecture, and inference-time optimization under real constraints. -
Distributed Computing
Reliable coordination, consensus under partial failure, CRDTs, and deterministic replay. -
Edge & Embedded Intelligence
FPGA acceleration, quantized inference, and microarchitecture-level design for real-time workloads. -
Automation & Platform Engineering
GitOps, reproducible MLOps workflows, infrastructure as code, and cloud-native design.
-
Retrieval-Native Language Models
Augmenting LLMs with vector-native memory and Bayesian routing. -
Micro-Containerized CPU Architecture (Patent Pending)
Sub-core orchestration for efficient AI workload scheduling on traditional CPUs. -
The Illusion of Boundless AI
Exploring architectural and ethical boundaries in scaling machine learning systems.
-
FPGA-based inference pipelines
INT4/INT8 quantization with speculative execution and register renaming. -
Distributed consensus engines
Vector clocks, quorum protocols, and tunable consistency in adversarial networks. -
Probabilistic inference
BNNs with Hamiltonian Monte Carlo and variational optimizers for uncertainty-aware prediction.
I host a short-form podcast translating research papers and system design principles into actionable insights.
Engineers, ML practitioners, and architects use it to bridge the gap between theory and production.
-
M.Eng., Computer Engineering
Dartmouth College (in progress) -
MBA, General Management
Cornell University (in progress) -
B.S., Software Engineering
The Pennsylvania State University
“Most practical systems research is invisible by design. I’m interested in the parts that make things work and the boundaries where they break.”