Research Engineer: Adversarial RL for AI Security

General Analysis; San Francisco, Northern (CA, KY); Hybrid; USD 150,000 - 210,000; Full time

Job summary

General Analysis is a frontier security lab focused on evaluating and strengthening frontier models for cyberdefense tasks. You will contribute to post-training models for adversarial capabilities using reinforcement learning in a distributed setting.

You’ll handle data generation, environment design, and evaluations across the training pipeline, applying novel methods to data-constrained and low signal-to-noise environments while advancing adversarial simulations for real-world enterprises.

Qualifications

• Experience with reinforcement learning or ML research (academic or industry).
• Publications in top venues (NeurIPS/ICML/ICLR/CVPR/ACL or similar).
• Security experience or interest in building security capabilities.

Responsibilities

• Responsible for post-training models for adversarial capabilities using reinforcement learning.
• Work on the entire training pipeline from data generation and environment design to evaluations.
• Tackle engineering challenges in distributed systems and improve algorithms for adversarial simulations.

Skills

PyTorch

RL infrastructure

Post-training infrastructure

Adversarial simulations

Tools

Tinker

verl

Job description

General Analysis is a frontier security lab focused on evaluating and strengthening frontier models for cyberdefense tasks. You will contribute to post-training models for adversarial capabilities using reinforcement learning in a distributed setting.

You’ll handle data generation, environment design, and evaluations across the training pipeline, applying novel methods to data-constrained and low signal-to-noise environments while advancing adversarial simulations for real-world enterprises.