Miguel Santos, ai security engineer

Miguel Santos

Senior AI Security Engineer

Mexico City, Mexico · America/Mexico_City (UTC-6) · 7 years of experience

Miguel focuses on securing AI applications, data paths, model supply chains, and agent permissions.

Request a shortlist

Why this profile fits

AI-specific threat modeling

Covers prompt injection, sensitive-data exposure, unsafe tool use, model supply chains, and excessive agency.

Least-privilege architecture

Scopes identities, tools, data access, secrets, and network paths to the minimum required for each workload.

Adversarial validation

Turns abuse cases and incidents into repeatable tests, monitoring signals, and response playbooks.

Relevant toolkit

Threat ModelingIAMKubernetes SecurityLLM Red TeamingSIEM

Delivery evidence

Selected work

Generative AI Red-Team Programme

consumer platforms

Designed and delivered a AI security programme focused on AI red teaming and abuse testing; identified and remediated 38 exploitable model-abuse paths before a public launch. The release included threat models, least-privilege controls, adversarial tests, logging, and incident playbooks mapped to OWASP guidance.

Threat ModelingPython

Abuse Case Regression Suite

consumer platforms operations

Built the supporting control and measurement layer for the primary system, covering review queues, regression checks, operational visibility, and a documented handoff to the owning team.

Threat ModelingKubernetes Security
View more profile detail →

Relevant experience

Career timeline

Senior AI Security Engineer

2024–Present

Devlyn client assignments · Remote

  • Led AI red teaming and abuse testing delivery for a consumer platforms team and identified and remediated 38 exploitable model-abuse paths before a public launch.

AI Security Engineer

2020–2023

consumer platforms product company (confidential) · Mexico City, Mexico

  • Built production systems in consumer platforms, with increasing ownership of reliability, testing, and stakeholder delivery.

Skill depth

Show experience in context.

VerbalCommunicationDomainUnderstandingProblemSolvingCodeQualitySystemDesignDeliverySpeed
Competency shapeAssessment across the same six dimensions used for every profile.

Relevant experience by skill

Threat Modeling7 years
Python6 years
IAM5 years
Kubernetes Security4 years
LLM Red Teaming7 years
SIEM6 years
See the complete skill index

Languages

PythonTypeScriptSQLBash

Frameworks

PythonIAMKubernetes SecurityOPAVaultSemgrep

Tools

Burp SuiteFalcoTerraformGitHub ActionsDocker

Platforms

AWSGoogle CloudAzureKubernetes

Storage

VaultS3PostgreSQLSecurity Lake

Paradigms

Secure-by-design AIZero trustAdversarial testingSupply-chain security

Credentials

Certifications

Certified Secure Software Lifecycle Professional

ISC2 · 2025 · Certified

AWS Certified Security – Specialty

Amazon Web Services · 2024 · Certified

Communication

Languages

English

Fluent

More examples

Similar AI Security Engineer profiles.