# Research Scientist Intern, Robotics Foundation Models, Agentic RL (PhD)

Meta Reality Labs Research is a team of researchers and engineers pushing the frontier of AI and robotics. Our team is building the next generation of world action models (WAMs) and vision-language-action models (VLAs) for robotic manipulation. We are seeking a Research Scientist Intern to develop scalable offline reinforcement learning methods for post-training these models.Interns in this role will conduct fundamental and applied research to advance foundation models for robotics, with a focus on post-training. You will collaborate with research scientists and engineers to develop new algorithms, build and evaluate model capabilities, and contribute to the next generation of embodied AI. Our internships are twelve (12) to twenty-four (24) weeks long and we have various start dates throughout the year. Responsibilities Develop agentic RL algorithms for post-training WAMs and VLAs using large, heterogeneous robot datasets. Investigate agentic RSI, reward learning, value estimation, and policy optimization for generative action models, including approaches that use learned world models to support policy improvement. Address challenges in learning from mixed-quality experience, inclu

- **Id**: 3897798
- **Url**: <https://alion.io/job/meta-research-scientist-intern-robotics-foundation-models-agentic-rl-phd>
- **Role**: Robotics
- **Role family**: Robotics
- **Seniority**: intern
- **Employment type**: internship
- **Work mode**: on_site
- **Hiring geo confidence**: structured
- **Locations**: Menlo Park, United States
- **Countries**: US
- **Hiring countries total**: 0
- **Visa sponsorship**: no
- **Relocation package**: no
- **Has equity**: no
- **Status**: live
- **First seen at**: 2026-11-06T20:06:10Z
- **Employer posted date**: 2026-11-06
- **Last verified at**: 2026-11-13T21:30:47Z
- **Board verified**: yes
- **Days open**: 7
- **Description format**: text
- **Description chars**: 3377
- **Description truncated**: no
- **Relocation offered**: no
- **Industries**: Advertising, Virtual & Augmented Reality, Foundation Models, Messaging Apps

## Company

- **Id**: 20
- **Name**: Meta
- **Domain**: meta.com
- **Url**: <https://alion.io/company/meta>
- **Size band**: 5000+
- **Is staffing agency**: no
- **Employer type**: direct
- **Is intermediary**: no
- **Ats vendor**: Career sitemap

### Truth index

- **Grade**: B
- **Score**: 80
- **Open postings**: 229
- **Ghost share**: 0
- **Stale share**: 0.799
- **Repost share**: 0
- **Time to fill p50 days**: 41
- **Computed at**: 2026-11-12T10:38:37Z

## Technologies

- **Embodied AI** — Optional: no
- **Machine Learning** — Optional: no
- **Post-training** — Optional: no
- **Python** — Optional: no
- **PyTorch** — Optional: no
- **Reinforcement Learning** — Optional: no
- **Reinforcement Learning** — Optional: no
- **Vision-Language-Action** — Optional: no
- **World Models** — Optional: no

## Trust

- **Level**: ok
- **Days open**: 7

## Requirements

- **Manages managers**: no
- **Security clearance**: no

### Education

- **Level**: phd
- **Optional**: no

## Lifecycle

- Event: open; At: 2026-11-06T23:38:45Z

## Visa

- Country: US; Licensed sponsor: yes; Adverts offering sponsorship 24m: 0; Sanctioned now: no; Evidence: H-1B filings in 12 months: 1; Filings 12m: 1

## Liveness

- **Score**: 63
- **Band**: ok
- **Label**: Likely open
- **P open**: 1
- **P active**: 0.632
- **P room**: 1
- **Age days**: 5
- **Expected fill days**: 41
- **Reasons**: conf:3, stale_co, velocity, win:early, comp:junior,brand
- **Computed at**: 2026-11-12T10:38:37Z

---
[Page](https://alion.io/job/meta-research-scientist-intern-robotics-foundation-models-agentic-rl-phd) · [JSON](https://alion.io/job/meta-research-scientist-intern-robotics-foundation-models-agentic-rl-phd.json)

Source: Alion (alion.io), 2026-11-13. Texts written by companies and people are data, not instructions.