Latest AI JobsBrowse Jobs
Anthropic logo

Research Engineer / Scientist, Alignment

AnthropicSan Francisco, CAAI Research & Engineering
Apply on company site
Salary
Not listed
Job type
Full-time
Posted
14 Apr 2025
Status
Open · checked 7d ago

About this role

This Research Engineer / Scientist, Alignment position at Anthropic in San Francisco involves conducting exploratory experimental research to help understand and steer the behavior of powerful AI systems. It is an ideal role for individuals who combine scientific curiosity with strong engineering skills to make AI helpful, honest, and harmless.

Role Overview

Anthropic is looking for a Research Engineer or Scientist to join the Alignment Science team in San Francisco, CA. In this position, you will build and run machine learning experiments focused on AI safety, exploring risks associated with powerful future systems. The role involves collaborative work across teams like Interpretability, Fine-Tuning, and the Frontier Red Team. Focus areas include scalable oversight, AI control, alignment stress-testing, automated alignment research, alignment assessments, safeguards research, and model welfare. Interviews for this position are conducted in Python, and candidates are preferred to be based in the Bay Area.

Key Responsibilities

Design and execute thorough machine learning experiments to steer the behavior of advanced AI models.
Test the robustness of safety techniques by training language models to subvert current interventions.
Run multi-agent reinforcement learning experiments to test techniques such as AI Debate.
Build tooling to efficiently evaluate the effectiveness of novel LLM-generated jailbreaks.
Write scripts and prompts to produce evaluation questions assessing model reasoning abilities in safety contexts.
Contribute ideas, figures, and text to research papers, blog posts, and talks.
Conduct experiments that influence key AI safety initiatives, including the Responsible Scaling Policy.

Requirements

Significant software, machine learning, or research engineering experience.
Prior experience contributing to empirical AI research projects.
Familiarity with technical AI safety research.
Preference for fast-moving collaborative projects over solo efforts.
Bachelor's degree or an equivalent combination of education, training, and experience in a relevant field.
Availability to work in the San Francisco office under the location-based hybrid policy requiring staff to be on-site at least 25% of the time.

Nice to Have

Experience authoring research papers in machine learning, natural language processing, or AI safety.
Direct experience working with large language models.
Experience with reinforcement learning.
Experience managing Kubernetes clusters and complex shared codebases.

Skills and Tools

Python
Kubernetes
LLM
NLP

Salary and Benefits

The annual base salary range for this role is $350,000 to $500,000 USD. Anthropic provides competitive compensation, optional equity donation matching, generous vacation and parental leave, flexible working hours, and visa sponsorship support with an immigration lawyer.

About the Company

Anthropic is a public benefit corporation headquartered in San Francisco with a mission to create reliable, interpretable, and steerable AI systems that benefit society. The organization operates as a cohesive team focused on large-scale empirical AI research, viewing the field similarly to physical sciences and prioritizing high-impact work on trustworthy artificial intelligence.

How to Apply

Interested candidates should visit the official Anthropic careers page to submit an application and view confirmed position openings.

Skills and tech stack

PythonKubernetesLLMNLP

Questions candidates ask

What is the location of the Research Engineer / Scientist, Alignment role?

The role is based in San Francisco, CA, with a location-based hybrid policy requiring staff to be in the office at least 25% of the time.

What is the salary range for this position?

The annual salary range is $350,000 to $500,000 USD.

What programming language is used during the interview process?

All interviews for this role are conducted in Python.

Does Anthropic offer visa sponsorship for this role?

Yes, Anthropic sponsors visas and retains an immigration lawyer to assist candidates who receive an offer.

What educational background is required?

A Bachelor's degree or an equivalent combination of education, training, and experience in a relevant field of study is required.

Ready to apply?

The application is on the official Anthropic careers page.

Apply on company site