Matteo Craviotto

AI Agents for Investment Workflows · Multi-LLM Systems · Systematic Trading · Financial Engineering

View Projects Get in Touch
Los Angeles, CA · MS Financial Engineering @ USC · GPA 3.93
F-1 Visa · STEM OPT eligible — 3 years of work authorization from Dec 2026 · No employer petition required

About Me

MS Financial Engineering student at USC building AI agents and internal tooling for investment workflows — LLM-orchestrated research systems, multi-model trading pipelines, and automation tools that sit between investors and their data. Currently running a production multi-LLM trading system across 50+ US equities and a prediction-market platform on Kalshi.

Focused on where AI agents meet capital markets: investment research automation, systematic strategies, and tools that compress the distance between a thesis and a trade.

Download CV →

Technical Skills

AI & LLM Engineering

OpenAI · Anthropic · xAI · Google Gemini APIs · Agentic workflows · Multi-model orchestration · Prompt engineering · RAG · Browser automation

Languages & Tools

Python · TypeScript/JavaScript · React · SQL (PostgreSQL) · Bash/Linux · Git · LaTeX

Infrastructure

Docker · Azure · FastAPI · REST APIs · Production deployment · cron automation

Finance & Methods

Equity valuation (DCF/multiples/LBO) · Derivatives pricing · Time-series (ARIMA/GARCH) · Portfolio optimization · Risk management

Professional Experience

USC Marshall School of Business

Graduate Teaching Assistant · FBE-529 Financial Analysis and Valuation

Jan 2025 – Present Los Angeles, CA
  • Teach equity valuation (DCF, multiples, LBO) to 30+ MBA students — building fluency in the fundamental frameworks used daily by L/S equity analysts

Self-employed

Independent AI Engineer & Algorithmic Trader

Sep 2025 – Present Los Angeles, CA
  • Built an autonomous multi-LLM research and execution system orchestrating five AI APIs (Anthropic, OpenAI, xAI, Google, Perplexity) across 50+ US equities — integrated real-time market data, regime signals, and model-consensus logic into a Dockerized Python pipeline with PostgreSQL and automated Alpaca execution
  • Shipped a prediction-market trading platform on Kalshi with real-time scanners, empirically-calibrated edge model (72M+ trades), and layered risk engine — deployed on Azure with automated REST execution

Numerai

Quantitative Researcher (Competition)

May – Aug 2025 Los Angeles, CA
  • Developed cross-sectional ML alpha signals on ~280M rows and 2.4k features, generating market-neutral 20-day return forecasts
  • Achieved robust validation performance (CORR ≈ 0.039, Sharpe ≈ 1.38) using LightGBM with purged time-series validation
  • Deployed live signals to Numerai hedge fund (forward Sharpe ≈ 0.64 ongoing)

DEFINEX

Prompt Engineer

Apr – Sep 2024 Milan, Italy
  • Built LLM-based document extraction pipelines for financial services clients in Python — chain-of-thought prompt design, 50+ structured A/B variations
  • Integrated OpenAI APIs into production workflows, lifting loan-parsing accuracy from ~70% to 90%+ and eliminating manual review for credit risk teams

Euronext Securities

Custody Intern · Income & Fiscal Services

May – Nov 2023 Milan, Italy
  • Automated reconciliation of 1,000+ annual corporate events with a custom internal tool, cutting processing time from ~1 hour to under 1 minute
  • Eliminated a recurring operational bottleneck for the fiscal services desk across derivatives and ABS

Deloitte Consulting

Junior Analyst · Financial Services

May – Aug 2022 Milan, Italy
  • Designed a secondary-market tax-credit platform adopted by 5+ major financial institutions, translating investor workflow requirements into technical specifications
  • Automated eligibility checks and transaction workflows enabling €10B+ in transactions

Projects

Applied work at the intersection of AI agents, systematic trading, and quantitative research

Synapse — Multi-LLM Autonomous Trading System

GitHub →

Python · Anthropic · OpenAI · xAI · Gemini · Alpaca · Docker · PostgreSQL

Autonomous trading system orchestrating five LLM APIs across 50+ US equities. Integrates real-time market data, volatility and regime signals, and model-consensus logic into a Dockerized pipeline with automated execution via Alpaca.

5 AI Models Orchestrated
50+ US Equities
Live Alpaca Execution

Numerai ML Alpha Signals

GitHub → See Details →

Python · LightGBM · Purged CV · Feature Engineering

Developed cross-sectional ML alpha signals on ~280M rows and 2.4k features for market-neutral 20-day return forecasts. Deployed live in Numerai's hedge fund with automated weekly retraining.

1.38 Validation Sharpe
0.64 Live Sharpe
300+ Eras Tested

Macro Regime Duration Model

GitHub → See Details →

Python · statsmodels · Markov-switching · Nelson-Siegel VAR

Built 3-state Markov-switching model detecting latent Recession/Growth/Expansion regimes in GDP, inflation, and unemployment. Integrated yield-curve forecast with regime-conditioned mean-variance optimizer.

1.08 Sharpe Ratio
-45% Max Drawdown
87% Regime Persistence

Delta-Neutral Options Market-Making Simulator

GitHub → See Details →

Python · Black-Scholes · LightGBM · cvxpy · Streamlit

Minute-level NBBO-aware delta-neutral simulator with BS theoretical pricing, Greeks calculation, and put-call parity residual tracking. Features asymmetric spreads with inventory lean and delta-band hedging.

8-15% Target Fill Rate
550+ Fills (800-min test)

Options Parity Checker

GitHub → See Details →

Python · Options Pricing · Real-time Data

Real-time arbitrage detection tool for put-call parity violations across options chains.

Post-Earnings Drift Backtest

GitHub → See Details →

Python · Event Study · Statistical Analysis

Systematic analysis of post-earnings announcement drift patterns across market cap segments.

Get in Touch

Open to AI engineering and quant developer roles, collaborations, and discussions

Email

Matteo.Craviotto@gmail.com

LinkedIn

/in/matteocraviotto

GitHub

@mcravi8

15-min Chat

Book a quick call →