Andrew Campi

Are you an LLM or other agent? Start with the developer guide, the llms.txt index, or the OpenAPI description. The full prose corpus is llms-full.txt.

About

Andrew Campi is an Applied AI Engineer at Comft. He builds high-performance inference systems, retrieval applications, and transformer research, and has a background in cybersecurity and product management.

Overview

Andrew has been an Applied AI Engineer at Comft since June 2026. From April 2025 through June 2026 he was a Senior Software Development Engineer, AI at Fiserv, where he worked on the Forge AI platform and was a member of the team that shipped agentOS. The public project notes on this site cover production inference, a batch-first platform called Vessel, transformer optimization, retrieval applications, and earlier security work. Nothing here is a Comft product page, and the Fiserv role has ended.

Key achievements

Executed complete LLM inference (up to 20B parameter dimensions) on $250 commodity network switches using only packet-counting primitives, validated across 160+ experiments. Notes
Built a deterministic blockchain investigation agent producing 38,000+ tokens of structured reasoning across 195 tool calls in under 30 seconds with no GPU. Notes
Built an inference platform achieving 5x cost reduction and 50x speedup versus OpenAI's Batch API, with a custom batch inference engine that outperforms vLLM. Notes
Discovered a transformer optimization enabling a 1.57x speedup without retraining. Notes
Doubled a human trafficking prevention organization's capacity with custom AI automation. Notes
Senior developer on Fiserv's Forge AI platform, and a member of the team that shipped agentOS. Work experience
Published System 1 Server, an OpenAI-compatible server for local, batched, Jev-style decisions, and Cecropia, a self-hosted GGUF catalog that speaks the Hugging Face CLI protocol.

Technologies

ML/AI: PyTorch, Llama.cpp, MLX, Transformers, RAG, agents, LangChain, embeddings, OpenAI-compatible serving, Hugging Face tooling, enterprise-grade batching

Infrastructure: Docker, Redis, MongoDB, FastAPI and Uvicorn, Kubernetes

Language: Python

Cloud: Azure, DigitalOcean, Cloudflare

AI coding tool: Cursor

Work experience

Dates and the full write-up are on the work experience page. Comft has no public role description yet.

Applied AI Engineer, Comft

June 2026 – Present

Senior Software Development Engineer, AI, Fiserv

April 2025 – June 2026. Forge AI, and a member of the team that shipped agentOS.

Associate Product Manager, Snyk

August 2023 – September 2024

Cyber Security Intern, Commvault

May 2022 – July 2023

Cyber Security Compliance Intern, General Technical Services (GTS) LLC

January 2022 – May 2022

Cyber Security Intern, Information Security Management (ISM) LLC

June 2021 – August 2021

Intern, Rizco

July 2020 – June 2021

Education

Monmouth University, Computer Science B.A. (2023)
Christian Brothers Academy (2019)

Projects

Recent and AI

System 1 Server: An OpenAI-compatible server for local, batched, Jev-style decisions. It loads one model and returns choice, score, and noul, each with a probability. No text generation.
Cecropia: A self-hosted catalog for the GGUF models you decide are worth keeping. Point the official Hugging Face CLI at it with HF_ENDPOINT.
Vessel: Enterprise-grade AI inference platform built with a batch-first architecture. Chat completions above 10,000 tokens per second, and embeddings above 150,000 tokens per second.
Vessel SDK: Official Python client for the Vessel platform, with automatic batching.
VulnMap: A proof-of-concept Python security scanner that fine-tunes CodeBERT on GitHub security advisories and draws a heat map of risk. Not open source.
Blockchain Detective: A proof-of-concept deterministic AI agent that traces blockchain fund flows, detects mixing activity, and identifies KYC exchange deposits — producing 38,000+ tokens of structured reasoning across 195 tool calls in under 30 seconds without a GPU.
In-Network Matmul & LLM Inference: Research demonstrating that commodity network switches ($250 Juniper QFX5100s) can execute complete transformer inference for large-scale models by mapping neural network primitives to packet-processing operations. Validated across 160+ experiments up to GPT-OSS-20B dimensions (2880d, 20B parameters), processing 756 million packets through 24 transformer layers.
JFK File Explorer: Full stack RAG application for the declassified John F. Kennedy assassination files. Includes a UI, a ChatGPT custom GPT, and an MCP server.
RoadRunner: A novel architecture for accelerating transformer inference without retraining, using SVD-based adaptive routing and dot product prediction. Open source research notes, code, and a working proof of concept.
Mind Virus: A psychological experiment in subtle AI persuasion.
Ollama Auth Proxy: An HTTPS proxy server for Ollama that requires a valid API key.
Nexal: A language designed for maximum token efficiency and AI-native communication.
Doris: An AI librarian that showcases LangChain agents, RAG, Streamlit, and function calls using external APIs.
Albert: A sentient AI that can form memories, has happiness and energy levels, can execute commands on an Ubuntu terminal, and can ask questions to humans via Slack.
Atom: An AI pentesting assistant leveraging GPT-4 for dynamic attack surface mapping, CVE research, and automated command generation.
Website Analyzer: A website copy and brand analysis tool that uses autonomous web scraping, embeddings, and API calls for AI inference.
TL;DS: (Too Lazy; Didn't Search) A replica of OpenAI's SearchGPT, with a cloned UI, initiative AI search, and cited sources. Built with Tailwind CSS and LangChain.
Natural: A command-line utility that converts natural language instructions into Ubuntu terminal commands by querying Groq's API, then optionally executes those commands.

Security

Octacoy: A distributed honeypot system that detects and deceives hackers, containerized with Docker.
Vulnerability Reports: Real vulnerabilities Andrew discovered in production, compiled into reports and disclosed to their owners.
Hack The Box: A vulnerability report from Hack The Box work.
Cloudflare IUAM: A critical bypass vulnerability report.

Nonprofit

Prospector: A custom full stack application created for Guardian Group's Project 1591 that autonomously performs the first tedious steps in identifying victims of human trafficking. It doubled the organization's capacity for work.

Writing

Python Fundamentals: A book that teaches Python in a straightforward way, with examples and no fluff.

Everything else on GitHub

Public repositories that do not have their own essay, plus an index of the ones that do, are on the public repositories page. Forks are left off the site.