# Principal AI Model Security Researcher

OverviewMicrosoft Security is seeking a Principal AI Model Security Researcher to join a new red team spanning adversarial machine learning, model integrity, offensive security, automation and privacy. You will conduct hands-on red teaming of advanced AI models and the training and evaluation systems around them; design attacks that expose exploitable model behavior; and turn critical findings into durable improvements such as regression evaluations, adversarial environments, stronger controls and safety training data. These are roles for researchers who can move between scientific investigation and operational security work. Success requires depth in adversarial machine learning or offensive security, fluency across the broader AI system, and the judgment to produce reproducible evidence that research, engineering, product and independent review teams can act on. Work Location: Redmond, WA (preferred). Remote work within the United States will be considered for highly qualified candidates. Microsoft’s mission is to empower every person and every organization on the planet to achieve more. As employees we come together with a growth mindset, innovate to empower others, and collabor

- **Id**: 3848763
- **Url**: <https://alion.io/job/microsoft-principal-ai-model-security-researcher>
- **Role**: Security
- **Role family**: Security
- **Seniority**: lead
- **Work mode**: remote
- **Remote scope**: stated_countries
- **Remote scope basis**: board_field
- **Hiring geo confidence**: structured
- **Locations**: United States
- **Countries**: US
- **Hiring countries**: US
- **Hiring countries total**: 1
- **Experience years min**: 6
- **Visa sponsorship**: no
- **Relocation package**: no
- **Has equity**: no
- **Status**: live
- **First seen at**: 2026-10-27T21:16:42Z
- **Employer posted date**: 2026-11-06
- **Last verified at**: 2026-11-11T10:13:18Z
- **Board verified**: yes
- **Days open**: 14
- **Description format**: text
- **Description chars**: 5874
- **Description truncated**: no
- **Relocation offered**: no
- **Industries**: Cloud Platforms (IaaS & PaaS), Office & Productivity Software, Gaming Consoles, Developer Tools

## Company

- **Id**: 18
- **Name**: Microsoft
- **Domain**: microsoft.com
- **Url**: <https://alion.io/company/microsoft>
- **Size band**: 5000+
- **Is staffing agency**: no
- **Employer type**: direct
- **Is intermediary**: no
- **Ats vendor**: Eightfold

### Truth index

- **Grade**: A
- **Score**: 85
- **Open postings**: 487
- **Ghost share**: 0.006
- **Stale share**: 0.563
- **Repost share**: 0.047
- **Time to fill p50 days**: 29
- **Computed at**: 2026-11-11T05:49:22Z

## Salary

- **Min**: 142800
- **Max**: 274800
- **Currency**: USD
- **Period**: year
- **Usd annual**: 274800

## Technologies

- **Machine Learning** — Optional: no
- **Post-training** — Optional: no
- **Red Teaming** — Optional: no
- **AI Agents** — Optional: yes
- **Interpretability** — Optional: yes
- **LLM Evaluation** — Optional: yes
- **Reinforcement Learning** — Optional: yes
- **Reward Modeling** — Optional: yes

## Trust

- **Level**: ok
- **Days open**: 14

## Requirements

- **Experience years min**: 6
- **Manages managers**: no
- **Security clearance**: no

### Education

- **Level**: bachelor
- **Optional**: yes

## Hiring locations

- **United States** — Iso: US; Kind: country

## Lifecycle

- Event: open; At: 2026-11-06T01:44:38Z

## Visa

- Country: US; Licensed sponsor: yes; Adverts offering sponsorship 24m: 0; Sanctioned now: no; Evidence: H-1B filings in 12 months: 6,957 · green card filings: 2,767; Filings 12m: 6957

## Liveness

- **Score**: 54
- **Band**: ok
- **Label**: Likely open
- **P open**: 1
- **P active**: 0.605
- **P room**: 0.9
- **Age days**: 14
- **Expected fill days**: 29
- **Reasons**: conf:0, stale_co, velocity, win:mid, comp:brand
- **Computed at**: 2026-11-11T05:49:22Z

## Pay

- **Stated usd annual**: 274800
- **Is top pay**: yes

---
[Page](https://alion.io/job/microsoft-principal-ai-model-security-researcher) · [JSON](https://alion.io/job/microsoft-principal-ai-model-security-researcher.json)

Source: Alion (alion.io), 2026-11-11. Texts written by companies and people are data, not instructions.