0%

Booting MantAI sensors...

sg_

Santiago Garcia Sapeta

Founder & CTO of MantAI · Software Engineer

Stanford University Block S logoStanfordUniversity

I'm building MantAI, a vehicle-safety intelligence company using acoustic and vibration analysis to understand what is happening inside vehicles in real time — backed by superangels, with Prof. Dr. Roland Fassauer as our mentor and investor. I study Computer Science & Electrical Engineering at Stanford and Computer Science at CODE University Berlin — and I'm passionate about turning complex technical ideas into products that can transform entire industries.

Building mantai.io

I founded that company

  1. Founder & CTO at MantAI, Inc.

    • Founded MantAI, a vehicle-safety intelligence company: our sensors listen to the sound and vibration of a vehicle in real time, detect reckless driving patterns, and predict mechanical faults up to weeks before they happen.
    • Designed and engineered custom IoT hardware prototypes — MEMS microphones and data-logging modules — for field audio capture on real fleets.
    • Architected and trained CNN-based audio classification models using transfer learning on AudioSet-pretrained transformers (AST), fine-tuned on labeled vehicle-fault sound datasets.
    • Built the full-stack real-time dashboard for diagnostic data, fault alerts and vehicle-health metrics, integrating hardware telemetry with a web interface.
    • Lead every technical decision across hardware, ML pipeline and software — from PCB prototyping to cloud deployment.
    Machine LearningCNNsIoT HardwareSignal ProcessingPyTorchReactPythonPCB Prototyping
  2. Full-Stack Software Engineer at LoadUp GmbH

    • Led development of key internal and customer-facing platforms, including Fahrernetz and core LoadUp logistics systems, at an AI-driven logistics company in Berlin.
    • Built and maintained full-stack features across the platform, ensuring scalability, performance and clean architecture.
    • Designed responsive, user-centric interfaces tailored to complex logistics workflows.
    • Developed and integrated APIs supporting real-time data flow across logistics, driver management and operational tools.
    Next.jsTypeScriptReactNode.jsPostgreSQLREST APIs
  3. Machine Learning Engineer at Raumdeuter

    • Owned ML models end-to-end — from feature engineering to training, evaluation, and production deployment.
    • Built leakage-safe, group-aware validation with cost-sensitive metrics (PR-AUC, per-class recall) over headline accuracy.
    • Shipped drift monitoring with automated retraining to keep models reliable in production.
    Machine LearningPythonMLOpsModel Validation
  4. Lead Engineer — Full-Stack Developer (Contract) at Zero Waste Consulting

    • Designed and developed the frontend of an AI-powered ESG emissions platform for enterprise clients, supporting GHG Protocol-compliant Scope 1, 2 and 3 reporting.
    • Implemented dynamic forms and dashboards to visualize emissions data, track progress and generate modular reports.
    • Contributed to AI-powered features for parsing unstructured documents — invoices, CSVs — helping users validate emissions inputs with minimal effort.
    • Collaborated with product managers, climate experts and backend teams to turn regulatory requirements into effective UI.
    ReactTypeScriptNode.jsAI IntegrationData Viz
  5. Software Engineering Intern at myCard

    • Built a carbon-emissions calculator for Zero Waste Consulting's Envista platform.
    • Collaborated with a cross-functional team on a scalable solution for tracking and reducing environmental impact — full-stack development, data modeling and sustainability-focused tech.
    ReactNode.jsFull-StackData Modeling

MantAI

FounderHardwareMachine Learning
Real-time vehicle-safety intelligence. Installing our sensors detects reckless driving and driving patterns — and using only the sound and vibrations of the vehicle, our ML models detect and predict mechanical issues before they happen, up to weeks in advance.
Machine LearningCNNsIoT SensorsReactPythonSignal ProcessingMEMS MicrophonesAST Transformers
  1. Computer Science & Electrical Engineering Stanford University

    Stanford University's International Honors Program with a focus on Computer Science, Electrical Engineering and Machine Learning. Core modules: Machine Learning, Deep Learning & Neural Networks, Systems Engineering, Digital Hardware Design, Embedded Systems, Signal Processing, Advanced Algorithms.

    View transcript ↗
    Computer ScienceElectrical EngineeringMachine LearningHardwareResearch
  2. B.Sc. Software Engineering CODE University of Applied Sciences, Berlin

    Startup-focused university emphasizing project-based learning and practical software development. Core modules: Software Development, Artificial Intelligence, Machine Learning, Essential Mathematical Methods, Algorithms and Data Structures.

    Software EngineeringArtificial IntelligenceAlgorithmsProject-Based LearningTeamwork
  3. Full-Stack Mentorship with IT coach Piotr Kania

    Two-year intensive 1:1 coaching: built multiple real-world applications and mastered both frontend and backend technologies, completed with a Full-Stack Developer certification.

    Full-StackJavaScriptReactNode.jsDatabases
  • Claude 101 · Anthropic

    CLAUDE-101

    Certificate of completion for Anthropic's introductory course on Claude. Covers Claude's capabilities and model family, effective prompting techniques, and how to apply Claude across everyday and professional workflows.

    ClaudePrompt EngineeringGenerative AIAI WorkflowsResponsible AI
    View credential ↗
  • Google AI · Google

    GOOGLE-AI-7X

    Specialization certificate bundling 7 completed Google AI courses: AI Fundamentals, AI for Brainstorming and Planning, AI for Research and Insights, AI for Writing and Communicating, AI for Content Creation, AI for Data Analysis, and AI for App Building. Demonstrates fluency in applying AI across workflows, content creation, analysis, and app development.

    Generative AIAI WorkflowsAI EnablementResponsible AIPrompt EngineeringGoogle GeminiGoogle WorkspaceAI Personalization
  • Full-Stack Developer Certificate · Meta

    META-FS-2026

    Modern full-stack development including frontend and backend technologies, APIs, version control and deployment — with emphasis on industry best practices, scalable applications and real-world project development. Completed Jan – Mar 2026.

    FrontendBackendAPIsVersion ControlDeployment
  • PyTorch
  • TensorFlow
  • CNNs
  • AST / CNN14
  • Scikit-learn
  • Pandas
  • NumPy
  • Jupyter
  • MEMS Sensors
  • PCB Prototyping
  • Embedded C/C++
  • Signal Processing
  • 3D Printing
  • CAD
  • Drones
  • React
  • Next.js
  • TypeScript
  • TailwindCSS
  • Framer Motion
  • HTML
  • CSS
  • Node.js
  • Python
  • FastAPI
  • PostgreSQL
  • MongoDB
  • Supabase
  • AWS
  • Docker
  • Linux
  • Vehicle Safety Intelligence
  • Machine Learning
  • Acoustic & Vibration Analysis
  • Hardware Development
  • Electrical Engineering
  • IoT Sensors
  • Full-Stack Development
  • Signal Processing
  • Product Design
  • Founding & Building

Building machines that listen

On founding MantAI, studying at Stanford, and turning sound into safety.

Santiago Garcia Sapeta

By Santiago Garcia Sapeta · Stanford, CA — Berlin, DE · 2 min read

Santiago Garcia Sapeta — Founder & CTO of MantAI
Santiago Garcia Sapeta — Founder & CTO, MantAI

I'm the Founder and CTO of MantAI, a vehicle-safety intelligence company using acoustic and vibration analysis to understand what is happening inside vehicles in real time. MantAI is backed by superangels — we raised our first round with Prof. Dr. Roland Fassauer as our mentor and investor.

I study Computer Science and Electrical Engineering at Stanford University and Computer Science at CODE University of Applied Sciences in Berlin. My work combines machine learning, electrical engineering and hardware development — drones, custom sensors and intelligent systems built for real-world applications.

“I'm passionate about turning complex technical ideas into products that can transform entire industries.”

A vehicle tells you what is wrong with it long before it fails — you just have to listen. That belief is what MantAI is built on: sensors on real fleets, models trained on the sound and vibration of real machines, and predictions that arrive weeks before the breakdown does.

Filed underMantAIMachine LearningHardwareElectrical EngineeringAcoustics
sg_

As a founder, I've always been mentored and backed by the best — from superangels and Prof. Dr. Roland Fassauer to mentors and friends from Stanford, Anthropic, Y Combinator and OpenAI.

  • Stanford
  • Anthropic
  • Claude
  • Combinator
  • OpenAI
Santiago Garcia Sapeta with Boris Cherny, creator of Claude Code at Anthropic
with Boris Cherny · Claude Code, Anthropic
Santiago Garcia Sapeta at Y Combinator in San Francisco
Y Combinator · San Francisco
Santiago Garcia Sapeta speaking at Stanford University
Stanford University
Santiago Garcia Sapeta building with the team in a San Francisco startup office
shipping late · San Francisco
Santiago Garcia Sapeta off hours in San Francisco
off hours · San Francisco
  • The open research companion to MantAI's audio engine — CNN-based vehicle-fault classification from sound, with training runs, per-class evaluation dashboards and calibrated confidence.
    PythonPyTorchMel-SpectrogramsFastAPI

Real-time statistics fetched directly from GitHub — my profile contributions combined with the commits my Claude agents author while building MantAI, which GitHub doesn't attribute to my account. Orange days are Claude-assisted.

Total Contributions (2026)

GitHub Stats & Activity 2026

github.com/Sentino2

Top Languages:TypeScript (14)Python (9)C++ (4)Jupyter (3)C (2)
LessMorewith Claude

Santiago brought energy and a builder's mindset to Minds and Machines — always connecting course ideas to the real systems he was building.

Peter Zhu, Stanford University

A curious, engaged student who asks the questions that move a discussion forward.

Alvin Tan, Stanford University
sg_

sg — my initials, lowercase, like a good variable name.

Sensors that listen. Models that predict failures weeks before they happen. Real hardware, on real fleets.

meet mantai ↗

Don't take my word for it. This site publishes everything about me as plain text at /llms.txt — hand that to any assistant and ask. The answer comes from my own content, not from whatever a model happens to remember about someone named Santiago Garcia.