Work

Shared access to AI models, with attention to failures, usage, and the cost of keeping it running.

• Python
• API design
• Reliability

Rebuilt a shared feature service in Rust and made it easier for model teams to adopt.

• Rust
• Async systems
• Performance

Shared persistence for agent sessions and tasks, with ongoing work on durable memory and retrieval.

• Rust
• Python
• API contracts

Built a retrieval assistant for technical knowledge and evaluated how well its answers stayed grounded in the source.

• Retrieval
• Evaluation
• Python

Operated shared model infrastructure and built migration tooling that checks artifacts, metadata, and prediction behavior.

• Python
• Model validation
• Migration tooling

Built an operations assistant with guarded actions, persistent state, and traces across the request flow.

• Python
• Tool interfaces
• Evaluation

Built shared clients, templates, and documentation to make platform services easier to use.

• Python
• SDK design
• Documentation

Built and operated shared tracing and evaluation infrastructure for AI applications.

• Tracing
• Evaluation
• Operations

Earlier work on model lifecycle tooling and shared monitoring for production ML.

• Rust
• Python
• Observability

Rebuilt a predictive system for live operational decisions and owned the path from training to serving.

• Python
• Model serving
• Applied ML

Improved a detection system through model development, labeling, and analysis of missed cases.

• Computer vision
• Python
• Evaluation

Worked on a leaner speech inference service with attention to latency, memory use, and operating cost.

• Rust
• Inference
• Performance

Evaluated location data changes against observed outcomes before an operational launch.

• Data analysis
• Validation

Built an analytical interface that helped operations teams explore patterns and investigate questions.

• Python
• Data visualization

Improved an operational measure by checking how recorded events corresponded to real activity.

• Data quality
• Analysis

A self-hosted Rust memory service for coding agents and local agents, built because existing OSS memory tools did not fit my namespace and control needs.

HTTP + MCP

one service for apps and agents

4 signals

hybrid recall fused at query time

~25 ms

p50 scoped recall, hybrid + rank

• Rust
• MCP
• Axum
• SQLite FTS5
• Qdrant
• ONNX

A self-hosted Rust remote-dev stack. Lobsterbox leases Docker or Hetzner runners, and lobsterfleet drives them from the browser with terminals, VNC desktops, and Codex-ready boxes.

Docker + Hetzner

leases from one CLI

Terminal + VNC

in the browser

Agent API

drive boxes headless

• Rust
• Axum
• Yew/WASM
• SQLite
• Hetzner
• Docker

A self-hosted experimentation platform where I try bleeding-edge tools and new methodologies on real infrastructure, from the network edge to GPU compute.

• Self-hosted
• Network segmentation
• Clustered compute
• SSO
• LLM gateway
• Remora

Research Assistant

Research assistant work at Ohio State using a Python scheduling app and operations research model for assigning incoming trailers to strip doors in a cross-dock.

Python

trailer assignment app

LP

strip-door scheduling model

DES

workforce and throughput simulation

• Python
• Linear programming
• Discrete-event simulation
• CPLEX

Research Assistant

A Markov chain Monte Carlo model for wind turbine maintenance that tested time-dependent failure rates and showed a 20% maintenance cost reduction in simulation.

20%

modeled maintenance cost reduction

MCMC

maintenance strategy simulation

Time-based

failure-rate modeling

• Python
• Markov chains
• MCMC
• Cost modeling

Simulation project

A discrete event simulation of an Ohio State cafe that tested self-ordering kiosks and workforce changes, showing a 16% modeled wait-time reduction and at least $288/day in savings.

16%

modeled wait-time reduction

$288/day

estimated daily savings

• Arena
• Discrete-event simulation
• Queueing
• Workforce analysis