# Researcher, Pretraining Safety

**Company:** [OpenAI](https://hotfix.jobs/companies/openai)
**Location:** San Francisco, CA
**Role:** AI Research
**Salary:** $295k – $445k/yr
**Skills:** PyTorch, JAX, Python, Apache Beam, LLMs, Diffusion Models, Multimodal Models, Statistical Reasoning, Data Pipelines, Evaluation Frameworks
**Posted:** 2025-10-30

> Develop techniques to predict and mitigate unsafe behaviors in early-stage base models, design safer pretraining architectures, and integrate safety signals throughout training. Collaborate across safety teams to build robust, scalable safety foundations grounded in real-world risks.

## Job Description

## Responsibilities
- Develop new techniques to predict, measure, and evaluate unsafe behavior in early-stage models
- Design data curation strategies that improve pretraining priors and reduce downstream risk
- Explore safe-by-design architectures and training configurations that improve controllability
- Introduce novel safety-oriented loss functions, metrics, and evals into the pretraining stack
- Work closely with cross-functional safety teams to unify pre- and post-training risk reduction

## Requirements
- Experience developing or scaling pretraining architectures (LLMs, diffusion models, multimodal models, etc.)
- Comfortable working with training infrastructure, data pipelines, and evaluation frameworks (e.g., Python, PyTorch/JAX, Apache Beam)
- Enjoy hands-on research — designing, implementing, and iterating on experiments
- Enjoy collaborating with diverse technical and cross-functional partners (e.g., policy, legal, training)
- Data-driven with strong statistical reasoning and rigor in experimental design
- Value building clean, scalable research workflows and streamlining processes

## Similar roles

- [Researcher, Misalignment Research](https://hotfix.jobs/jobs/a3216578-b6a0-4e63-95b9-226fbf1ddfc8) - OpenAI - San Francisco, CA - $295k – $445k/yr
- [Researcher, Loss of Control](https://hotfix.jobs/jobs/c0b2fb0d-2ac2-4d91-b893-9e38f4cfccc7) - OpenAI - San Francisco, CA - $295k – $445k/yr
- [Researcher, Synthetic RL](https://hotfix.jobs/jobs/1d48e4f7-9589-45b3-96ed-05276e32344e) - OpenAI - San Francisco, CA - $295k – $445k/yr
- [Research Engineer / Research Scientist, Post-Training](https://hotfix.jobs/jobs/84dfac6b-2704-4ec9-ac6c-666459514793) - OpenAI - San Francisco, CA - $295k – $555k/yr
- [Research Engineer, Codex](https://hotfix.jobs/jobs/9ccc8d20-02eb-474a-a9ad-68333add9933) - OpenAI - San Francisco, CA - $295k – $445k/yr

**Apply:** https://hotfix.jobs/jobs/5fa53d44-8b74-4ff3-9fc4-5eb917519229
**Canonical:** https://hotfix.jobs/jobs/5fa53d44-8b74-4ff3-9fc4-5eb917519229