# Researcher, Frontier Cybersecurity Risks

**Company:** [OpenAI](https://hotfix.jobs/companies/openai)
**Location:** San Francisco, CA
**Role:** ML Engineering
**Salary:** $295k – $445k/yr
**Skills:** Deep Learning, Transformer Models, PyTorch, TensorFlow, Data Structures, Algorithms, Software Engineering, LLMs, Knowledge Distillation, Supervised Fine-Tuning, Policy Optimization, Red Teaming, Threat Modeling, Cybersecurity, Abuse Prevention
**Posted:** 2026-08-03

> Design and deploy scalable safeguards that mitigate cybersecurity misuse by frontier AI models across OpenAI product surfaces. The role requires deep learning and transformer expertise, software engineering fundamentals, LLM fine-tuning experience, and cross-functional collaboration.

## Job Description

## Responsibilities
- Design and implement mitigation components for model-enabled cybersecurity misuse, spanning prevention, monitoring, detection, and enforcement.
- Integrate safeguards across product surfaces with product and engineering teams, ensuring protections are consistent, low-latency, and scalable.
- Evaluate technical trade-offs involving coverage, latency, model utility, and user privacy, and propose pragmatic, testable solutions.
- Collaborate with risk and threat-modeling partners to align mitigation design with anticipated attacker behaviors and high-impact misuse scenarios.
- Execute rigorous testing and red-teaming workflows against evolving threats, including novel exploits, tool-use chains, and automated attack workflows.
- Iterate on the mitigation stack based on testing findings across different product surfaces.

## Requirements
- Passion for AI safety and making cutting-edge AI models safer for real-world use.
- Demonstrated experience with deep learning and transformer models.
- Proficiency with PyTorch or TensorFlow.
- Strong foundation in data structures, algorithms, and software engineering principles.
- Familiarity with training and fine-tuning large language models, including distillation, supervised fine-tuning, and policy optimization.
- Ability to collaborate across research, security, policy, product, and engineering teams.
- Significant experience designing and deploying technical safeguards for abuse prevention, detection, and enforcement at scale.

## Nice to Have
- Background knowledge in cybersecurity or adjacent fields.

## Similar jobs

- [Software Engineer, Trainium](https://hotfix.jobs/jobs/5e1a8341-f0e9-45c8-8492-12782b38f079) - OpenAI - San Francisco, CA - $295k – $380k/yr
- [Applied AI Engineer, Beneficial Deployments](https://hotfix.jobs/jobs/c38bca51-e1c4-4f65-8790-b09d52d8169c) - Anthropic - San Francisco, CA - $280k – $320k/yr
- [Software Engineer, AI for Chip Design](https://hotfix.jobs/jobs/abfb017d-1ce2-4d24-901d-16084eb7b3bc) - OpenAI - San Francisco, CA - $266k – $468k/yr
- [Software Engineer, Model Runtime](https://hotfix.jobs/jobs/7f549613-3d04-42b8-b691-8ed7c2d9ecd1) - OpenAI - San Francisco, CA - $266k – $445k/yr
- [Machine Learning Engineer](https://hotfix.jobs/jobs/22efd49a-a0e5-48d7-aea3-8a7bdd7d7337) - Hyperbound - San Francisco, CA - $260k – $300k/yr

**Apply:** https://hotfix.jobs/jobs/0e83c34a-c3be-4ad7-84b8-7c64d7d2366b
**Canonical:** https://hotfix.jobs/jobs/0e83c34a-c3be-4ad7-84b8-7c64d7d2366b