Security engineer for AI agents

NeuralTrust

United States

Remote

USD 140,000 - 190,000

Full time

2 days ago
Be an early applicant

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Benefits offered by this job

Remote-friendly
Barcelona HQ
Конкурентная оплата

Job summary

NeuralTrust ищет инженера по безопасности для разработки и защиты AI-агентов на этапе эксплуатации. Ваша работа будет связана с Gateway TrustGate и TrustGuard, внедрением дефенсов против инжекций и утечек данных, а также настройкой потоков аутентификации для агентов и инструментов.

Требуется 3–5 лет опыта, знание Go или Python, опыт работы с Kubernetes/Docker и облачными сервисами. Английский язык на профессиональном уровне обязателен; удалённая работа по Европе, HQ в Барселоне, конкурентная

Qualifications

  • 3–5 лет опыта в разработке ПО или security.
  • Умение программировать на бэкэнде (Go или Python).
  • Владение веб и API безопасностью: OWASP Top 10, OAuth/OIDC/JWT.
  • Опыт облачных распределённых систем с Docker/Kubernetes.
  • Умение объяснять торговые-offsecurity инженерам и клиентам.
  • Уровень английского — профессиональный.
  • Плюсом: опыт с LLMs, агентскими фреймворками, китай-нет; знание OWASP для LLM и MITRE ATLAS; удалённость/gateway и пр.

Responsibilities

  • Разрабатывать security features для Agent Gateway (TrustGate) и TrustGuard.
  • Преобразовывать исследования угроз в production-защиту ( jailbreaks, exfiltration и пр ).
  • Строить иhardening flows аутентификации и авторизации для агентов и инструментов.
  • Проводить threat modeling и secure design reviews.
  • Сотрудничать с инженерами для раннего исправления проблем.
  • Улучшать качество детекции совместно с ML-командой, снижая ложноположительные результаты.
  • Охватывать безопасность на всём SDLC: обзор кода, сканирование зависимостей, secrets, CI/CD.
  • Помогать реагировать на security-issues от клиентов/исследователей.

Skills

Backend разработка
Go/Python
Web/API безопасность
Cloud distributed systems
Docker и Kubernetes
Английский язык
LLMs / агенты

Tools

Docker
Kubernetes
AWS
GCP
Azure
LangChain
OpenAI Agents SDK
MCP / A2A

Job description

Описание

AI agents are moving into production fast, and most companies have no way to see or control what those agents do. NeuralTrust is the security layer for AI agents. We’re a Barcelona-based company backed by a €20M seed round. Teams use our platform to secure their agents at runtime, govern how agents reach models and tools through our Agent Gateway, and test them against real-world attacks before attackers get there first. Gartner recognizes us in its Market Guides for Guardian Agents and for AI Gateways. Today we protect production AI workloads for customers across Europe and the US.

Задачи

Design and build security features for our Agent Gateway (TrustGate) and Agent Runtime Security (TrustGuard). Examples: prompt injection defenses, data loss prevention, tool and MCP access controls, rate limiting and policy enforcement. Turn research on emerging threats into production defenses. These include jailbreaks, indirect prompt injection, tool misuse and data exfiltration. Build and harden the authentication, authorization and identity flows for AI agents and the tools they call. Run threat modeling and secure design reviews for new features. Partner with engineers to fix issues early. Improve detection quality with the ML team, keeping both false positives and latency low. Own security across the SDLC for the products you touch: code review, dependency and container scanning, secrets management, and secure CI/CD. Help respond to security issues reported by customers or researchers.

Требования

3–5 years of experience in software engineering, product security or application security. Strong coding skills in at least one backend language. Go or Python is ideal. A solid grasp of web and API security: OWASP Top 10, authN/authZ (OAuth, OIDC, JWT), input validation, and secure API design. Experience building or securing distributed systems in the cloud (AWS, GCP or Azure), with Docker and Kubernetes. You enjoy shipping. You’d rather build the control than write the report about it. Clear communication and the ability to explain security trade-offs to engineers and customers. Professional working proficiency in English. Будет плюсом: Hands-on experience with LLMs, AI agents or agent frameworks (LangChain, OpenAI Agents SDK, MCP, A2A); Knowledge of the OWASP Top 10 for LLM Applications or MITRE ATLAS; Experience with AI or MCP gateways, reverse proxies or high-throughput, low-latency services; Background in detection engineering, WAFs or runtime protection; Contributions to open-source security projects, CVEs or bug bounty findings; Spanish is a plus

Условия

Work on one of the fastest-moving problems in security: protecting AI agents in production. Real ownership in a small, senior team where your work ships to customers quickly. Remote-friendly across Spain and the EU, with a Barcelona HQ for team time. Competitive salary.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Security engineer for AI agents
Security engineer for AI agents

Zencoder • United States

Remote
USD 140,000 - 190,000
Remote-first work
AI Agent Security Engineer - Production Guard (Remote)
AI Agent Security Engineer - Production Guard (Remote)

NeuralTrust • United States

Remote
USD 140,000 - 190,000
Remote-friendly
Barcelona HQ
Конкурентная оплата
Forward Deployed Security Engineer
Forward Deployed Security Engineer

TRUSTEQ GmbH • United States

Hybrid
USD 120,000 - 180,000
Flexible working models
30 days paid vacation
BahnCard
+6
AI Security Engineer | Pharma
AI Security Engineer | Pharma

Ambit Iberia • United States

Hybrid
USD 150,000 - 230,000
Medical insurance
Public transport ticket
Childcare support
+3
Cloud security engineer for AI agents
Cloud security engineer for AI agents

Connectis_ • United States

Remote
USD 34,000 - 75,000
Remote work
Milestone-based payments
Referral bonus PLN 5,000
Security engineer
Security engineer

NextLink Group • United States

Hybrid
USD 50,000 - 56,000
Security engineer for AI platforms
Security engineer for AI platforms

RMG Recruitment Agency • United States

Remote
USD 79,000 - 124,000
AI security researcher & engineer
AI security researcher & engineer

SpaceAI • United States

Hybrid
USD 140,000 - 190,000
Гибридный формат работы
Опционы/доля в компании
application security engineer for AI models
application security engineer for AI models

EPAM • United States

Remote
USD 120,000 - 170,000
DevOps engineer for AI agent platforms
DevOps engineer for AI agent platforms

EPAM • United States

Hybrid
USD 140,000 - 190,000
Office or home-friendly environment
Global mobility opportunities
Comprehensive learning resources