# Research Engineer / Scientist, Alignment Science

**Company:** [Anthropic](https://hotfix.jobs/companies/anthropic)
**Location:** San Francisco, CA
**Role:** AI Research
**Salary:** $350k – $500k/yr
**Skills:** Python, Machine Learning, LLMs, Reinforcement Learning, Kubernetes, Ai Safety, Scalable Oversight, Ai Control, Alignment Stress-Testing, Research Engineering
**Posted:** 2026-02-12

> Conducts experimental ML research on AI alignment and safety for powerful systems, focusing on scalable oversight, control, and stress-testing. Requires strong software/ML engineering, empirical research experience, and Python proficiency.

## Job Description

## Representative projects
- Testing robustness of safety techniques by training models to subvert interventions.
- Running multi-agent reinforcement learning experiments for techniques like AI Debate.
- Building tooling to evaluate LLM-generated jailbreaks.
- Writing scripts and prompts for safety-relevant reasoning evaluations.
- Contributing to research papers, blog posts, and talks.
- Running experiments for Responsible Scaling Policy implementation.

## You may be a good fit if you
- Have significant software, ML, or research engineering experience.
- Have experience contributing to empirical AI research projects.
- Have familiarity with technical AI safety research.
- Prefer fast-moving collaborative projects.
- Pick up slack beyond your job description.
- Care about AI impacts.

## Strong candidates may also
- Have experience authoring ML, NLP, or AI safety research papers.
- Have experience with LLMs.
- Have experience with reinforcement learning.
- Have experience with Kubernetes clusters and complex shared codebases.

**Note**: Interviews conducted in Python; Bay Area base preferred.

## Logistics
**Education**: Bachelor's degree in related field or equivalent experience.
**Location**: Hybrid policy - in office at least 25% of time.

## Similar roles

- [Research, Pre-Training Science](https://hotfix.jobs/jobs/1632c257-f81d-4db4-87a7-ee81864adee1) - Thinking Machines Lab - San Francisco, CA - $350k – $475k/yr
- [Research, Audio Expertise](https://hotfix.jobs/jobs/4d683697-adb2-4f5d-b26e-33ed1b92740c) - Thinking Machines Lab - San Francisco, CA - $350k – $475k/yr
- [Research Scientist, Interpretability](https://hotfix.jobs/jobs/b82b1f34-1f5f-4178-96bf-2c997705b2fe) - Anthropic - San Francisco, CA - $350k – $850k/yr
- [Research Engineer, Production Model Post Training](https://hotfix.jobs/jobs/2ef71372-28ac-4b00-b9c5-b955651a7ebc) - Anthropic - San Francisco, CA - $350k – $500k/yr
- [Research Engineer, Pretraining Scaling](https://hotfix.jobs/jobs/c57601ec-5c27-4553-ab57-05c56e8fad16) - Anthropic - San Francisco, CA - $350k – $850k/yr

**Apply:** https://hotfix.jobs/jobs/3f42e78a-0c41-4202-b05c-447f8dab7531
**Canonical:** https://hotfix.jobs/jobs/3f42e78a-0c41-4202-b05c-447f8dab7531