Research Engineer, Post-Training

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. We protect the world as AI systems grow more capable and more dangerous in the wrong hands. We build high-fidelity research infrastructure that evaluates and strengthens frontier models on critical cyberdefense tasks, and we bring that research directly to enterprises — securing the AI systems they deploy through adversarial testing and runtime protection.

About the role

As a Research Engineer, you will be responsible for post-training models for adversarial capabilities using reinforcement learning.

You will work on the entire training pipeline from data generation and environment design to evaluations.

You will tackle engineering challenges involving distributed systems, innovate new methods for data-constrained and low signal-to-noise environments, and make algorithmic improvements for applying trained models for adversarial simulations.

You may be a good fit if

• You are comfortable with PyTorch, RL infrastructure, post-training infrastructure, or tools such as Tinker and verl.
• You have academic and/or industry experience with reinforcement learning or machine learning research, or are eager to learn.
• You have publications in top-tier venues such as NeurIPS, ICML, ICLR, CVPR, ACL, or similar.
• You have security experience, or are excited to build it here.
• You have a high level of agency, strong technical acumen, and clarity of thought.

You'll thrive here if

• You are excited about applying novel research and new technology to real-world problems.
• You are excited to learn new domains and build deep context in AI security.
• You are results-oriented and can balance deep exploration with practical implementation.
• You proactively step outside defined boundaries to support the team's mission and unblock others.