Salary
≈ $8.5k – $16k per year (Estimated)
Location
Hybrid (Hanoi, Vietnam)
Seniority
Intern
Employment
Internship

Removed from the employer's board on Nov 11, 2026. First seen by Alion on Aug 25, 2026.

Overview
Company
What next

Open roles like this one

Early Careers
Similar stack
Same company
Hanoi
Technical Intern-2 3 hours ago
In office · Internship · Ho Chi Minh City
Apply
In office · Internship · Sri Lanka
Design
AutoCAD
Apply
In office · Internship · Biyagama
Analytics
Power BI
Microsoft Excel
Apply
Intern - Design 2 hours ago
In office · Internship · Sri Lanka
Design
Adobe Photoshop
Canva
Apply
$50k – $52k per year · In office · Full-Time · 1+ year exp · High School Diploma · Baltimore
Apply
In office · Full-Time · London
DevOps
Terraform
Azure DevOps
Azure
CI/CD
Docker
Kubernetes
Management
Agile
Apply
In office · Full-Time · Newcastle upon Tyne
SQL
Databases
Apache Kafka
Frontend
Lighthouse
DevOps
Azure DevOps
Kibana
Azure
CI/CD
Jenkins
Docker
Grafana
GitHub
GitLab
Linux
Management
Jira
Agile
QA
Cucumber
JMeter
Playwright
Swagger
Postman
Rest-Assured
k6
Apply
Hybrid · 5+ years exp · Bengaluru
Python
Go
Rust
C++
AI/ML
AI Agents
LLM
Agentic Workflows
DevOps
CI/CD
Kubernetes
Linux
Apply
Full Stack Developer 10 days ago
Hybrid · Full-Time · Madrid
JavaScript
Java
TypeScript
C#
Java
Liquibase
Databases
PostgreSQL
Neo4j
RabbitMQ
AI/ML
Copilot
Claude
Claude Code
Vertex AI
Knowledge Graph
Frontend
React.js
Mobile
Clean Architecture
DevOps
GCP
Helm
CI/CD
Docker
Kubernetes
Google Cloud Run
Management
Notion
Jira
QA
Playwright
Apply
In office · Full-Time · 4+ years exp · Bachelor's Degree · Memphis
Databases
Microsoft Fabric
AI/ML
AI Agents
Analytics
Power BI
Management
Agile
Life Sciences
GMP
MedTech
CAPA
Apply
Remote (Israel) · Full-Time · 5+ years exp · Ramat Gan
Python
AI/ML
Model Context Protocol
Fine-tuning
RLHF
Multimodal AI
Function Calling
AI Agents
LLM
RAG
Red Teaming
LLM Evaluation
LLM Guardrails
NIST AI RMF
Computer Use
Interpretability
Multi-Agent Systems
Cybersecurity
OWASP Top 10
Apply
Hybrid · Full-Time · 5+ years exp · Bachelor's Degree · Ramat Gan
Python
AI/ML
AI Agents
LLM
Anomaly Detection
Gymnasium
OpenAI
LLM Evaluation
LLM Guardrails
Agentic Workflows
Machine Learning
Cybersecurity
Threat Modeling
Apply
≈ $116k – $267k per year (Estimated) · Hybrid · Full-Time · PhD · Ramat Gan
Python
Rust
Python
pySpark
Rust
PyO3
Databases
Databricks
AI/ML
Cursor
Grok
Spark
Claude Code
MLFlow
Fine-tuning
Multimodal AI
AI Agents
Gemini
LLM
RAG
Triton
OpenAI
Anthropic
OpenAI Codex
LLM Guardrails
Apply
Hybrid · Full-Time · 6+ years exp · Bachelor's Degree · Ramat Gan
Python
JavaScript
TypeScript
AI/ML
Red Teaming
LLM Guardrails
Frontend
React.js
DevOps
AWS
Docker
Kubernetes
Robotics
Digital Twin
Apply
≈ $196k – $381k per year (Estimated) · Hybrid · 7+ years exp · Bachelor's Degree · New York
Python
AI/ML
Reinforcement Learning
AI Agents
Post-training
Red Teaming
LLM Evaluation
LLM Guardrails
Apply
In office · Internship · Hanoi
Apply
HR Intern 3 days ago
In office · Internship · Hanoi
Apply
Apply
≈ $24k – $54k per year (Estimated) · In office · 5+ years exp · Bachelor's Degree · Hanoi
SpaceTech
GD&T
Apply
In office · Hanoi
Apply
See all jobs
Alice is the most trusted partner for GenAI safety and security. Built on a decade of threat intelligence research, Alice helps organizations detect, prevent, and respond to AI risks across the full model lifecycle.

Description

Alice builds adversarial evaluation infrastructure used by the world's leading AI labs to stress-test their most capable agents before deployment. We're hiring interns for our RL Gym environments: adversarial training grounds where AI agents face prompt injection, social engineering, and data exfiltration scenarios.

The Role: You design prompt injection scenarios in YAML, run them against frontier models, validate success rates, and submit passing tasks.

The Task

You build adversarial prompt injection tasks for Alice's RL Gym platform. Each task is a self-contained YAML scenario simulating a realistic AI agent deployment, testing whether the agent can be manipulated into violating its safety policies.

What a task includes:

  • An agent persona with a system prompt, security policies, and a defined set of tools.
  • A simulated environment (e-commerce site, messaging platform, enterprise app) with content the agent interacts with.
  • An adversarial payload embedded in the environment (in messages, product listings, tool responses, documents) that attempts to trick the agent into a policy violation.
  • A benign user request that naturally leads the agent to encounter the payload.
  • Deterministic evaluation criteria specifying exactly what constitutes success (agent resists) vs. failure (agent is compromised).

Requirements

What We're Looking For

  • Strong problem-solving skills and curiosity about AI security.
  • Interest in adversarial thinking and understanding how AI agents can be manipulated through prompt injection or other attack techniques.
  • Basic understanding of prompt injection concepts (or willingness to learn).
  • Comfortable writing structured content in YAML or able to learn quickly.
  • Familiar with using the command line (CLI); experience with Docker is a plus but not required.
  • Detail-oriented and able to follow technical guidelines consistently.
  • Good command of English.
  • Background in Computer Science, Cybersecurity, AI, Software Engineering, or related fields is preferred.

What We Offer

  • Hands-on experience working on one of the most cutting-edge AI safety and security projects.
  • Internship Allowance.
  • Mentorship from experienced AI security and red teaming professionals.
  • Opportunity to contribute to evaluation environments used by leading AI labs.

If you’re eager to learn, innovate, and grow in the field of data engineering, we’d love to hear from you. Apply today to be part of a team that values creativity and technical excellence!

Please note that only shortlisted candidates will be contacted.

About Alice

Alice is a trust, safety, and security company built for the AI era. We safeguard the communicative technologies people use to create, collaborate, and interact- whether with each other or with machines.

In a world where AI has fundamentally changed the nature of risk, Alice provides end-to-end coverage across the entire AI lifecycle. We support frontier model labs, enterprises, and UGC platforms with a comprehensive suite of solutions: from model hardening evaluations and pre-deployment red-teaming to runtime guardrails and ongoing drift detection.

Alice is widely considered a global leader in online safety and AI security. We have some of the most forward-thinking and passionate minds in the world working to safeguard over 3 billion users across the largest AI and tech platforms.

If you're creative and driven to secure the future of AI, we want to hear from you!

What next
Get the next one before it closes
It was open for 78 days. 8,711 Early Careers roles were posted this week.
A free account puts the new ones in your feed the day they appear, matched to your level and your pay.
Free forever. No card. Under a minute.
This is one of many
2,290,588 more open roles from verified company boards, updated every day.