Andrew Campi Portfolio
Are you an LLM or a robot? View the machine readable version of this site here, or download the full context file here.
About
AI Engineer specializing in high-performance inference systems, RAG applications, and transformer architecture research. Background in cybersecurity with experience in penetration testing and vulnerability discovery.
Quick Overview
AI Engineer with strong experience building production ML systems. Core expertise: high-performance inference (10,000+ tok/s systems), transformer optimization research (novel 1.57x speedup architecture), and RAG applications. Previous work in cybersecurity and product management. Currently building agentic AI platforms at Fiserv serving hundreds of users.
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 here
- Built deterministic blockchain investigation agent producing 38,000+ tokens of structured reasoning across 195 tool calls in under 30 seconds with no GPU here
- Built inference platform achieving 5x cost reduction and 50x speedup vs OpenAI's Batch API, with a custom batch inference engine that outperforms vLLM here
- Discovered novel transformer optimization enabling 1.57x speedup without retraining here
- Doubled human trafficking prevention org's capacity with custom AI automation here
- Senior developer for Fiserv's ForgeAI platform
Core Technologies
ML/AI: PyTorch, Llama.cpp, MLX, Transformers, RAG, Agents, LangChain, Embeddings, Enterprise-grade Batching
Infrastructure: Docker, Redis, MongoDB, FastAPI+Uvicorn, Kubernetes
Language: Python
Cloud: Azure, DigitalOcean
AI Coding Tool: Cursor with Claude Sonnet
Work Experience
Senior Software Development Engineer, AI
Company: Fiserv
Duration: April 2025 - Present
- Developing the Forge AI platform, an AI agent platform that specializes in assisting Fiserv employees in understanding their documentation and resources
- Lead developer on the Context Service, a server that can intelligently process and ingest several file types (PDF, XLSX, PPTX, etc) so that AI assistants can use the data as context in chats, processing hundreds of unstructured files daily
- Independently identified, prototyped, and shipped production features including agentic planning and chained tool executions, LLM-as-a-judge, and OpenAI+Anthropic compliant API gateways to lower adoption friction
Associate Product Manager
Company: Snyk
Duration: August 2023 - September 2024
- Performed deep product research, competitive analyses, and interacted with customers to gain real feedback, all to best influence and improve Snyk's API landscape and platform
Cyber Security Intern
Company: Commvault
Duration: May 2022 - July 2023
- Invented and managed the development of the Metallic Attack Simulator, a GUI-based ethical hacking automation tool used by Metallic sales engineers to display the value of defensive products
- Developed the integration between Metallic and Palo Alto's Cortex XSOAR, enabling customers to automatically perform defensive actions on their backups based on detected threats using APIs and Azure KeyVault
- Led weekly training for team members, teaching the ethical hacker mindset, tools, and methodologies
- Performed digital forensics on compromised VMs in Azure, discovering the source of breaches and developing a timeline of attack
Cyber Security Compliance Intern
Company: General Technical Services (GTS) LLC
Duration: January 2022 - May 2022
- Assisted the GTS team with completing the CMMC certification at level two
- Gathered artifacts to be uploaded and approved by the auditor
- Worked closely with the GTS team members to complete the certification in a timely manner
Cyber Security Intern
Company: Information Security Management (ISM) LLC
Duration: June 2021 - August 2021
- Shadowed Penetration Tests and learned basic hacking tools and techniques such as Nmap and Dirbuster
Intern
Company: Rizco
Duration: July 2020 - June 2021
- Developed websites in Shopify and WordPress, created competitive analyses, graded advertisement campaigns
- Learned invaluable life lessons through communicating with team members, managing expectations, due dates, and shadowing professional client interactions and interviews
Education
-
Monmouth University, Computer Science B.A. (2023)
-
Christian Brothers Academy (2019)
Project Directory
AI Projects (newest to oldest)
-
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.
-
Vessel Platform: Enterprise-grade AI inference platform built using a batch-first architecture. Achieves chat completions at speeds over 10,000 tok/s, and embeddings at over 150,000 tok/s.
-
JFK File Explorer: Full stack RAG application enabling easy accessibility and readability into the John F. Kennedy assassination files recently declassified by the United States government. Features a clean UI, ChatGPT Custom GPT (to access directly via ChatGPT), and an MCP server (form agentic access).
-
RoadRunner: A novel architecture for accelerating transformer inference without retraining, using SVD-based adaptive routing and dot product prediction. Fully open source research notes, code, and 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 a collection of advanced AI programming methodologies, such as 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. Simplify and enhance your pentests with Atom's conversational UI and extensive API.
-
Website Analyzer: A website copy and brand analysis tool that uses a combination of autonomous web scraping, embeddings, and API calls for AI inference.
-
TL;DS: (Too Lazy; Didn't Search) A replica of OpenAI's SearchGPT, featuring a cloned UI, initiative AI search, and cited sources. Built with TailWind CSS and Langchain.
-
Natural: A completely free command-line utility that converts natural language instructions into actual Ubuntu terminal commands by querying Groq's API. It then optionally executes those commands.
Cyber Security Projects
-
Octacoy: A distributed honeypot system that detects and deceives hackers, containerized with Docker.
-
Vulnerability Reports: These are real vulnerabilities that Andrew discovered in production. Andrew compiled the discoveries into reports, and disclosed them to their owners.
Published Books
- Python Fundamentals: This book is designed to teach you everything you need to know about Python, presented in a straightforward manner with easy-to-understand examples and no fluff. It's the way Andrew wishes Python was taught to him when he first started learning.
Non-Profit Work
- Prospector: A custom full stack application created for Guardian Group's Project 1591 that autonomously performs the first tedious steps in the process of identifying victims of human trafficking. Successfully doubled the organizations capacity for work.