AI Safety Researcher

thinking machines lab • San Francisco Bay Area

Visa Sponsorship Relocation

This Job is No Longer Active This position is no longer accepting applications

AI Summary

Thinking Machines Lab is hiring an AI Safety Researcher to ensure models are safe and trustworthy. The role combines research with hands-on technical work across data curation, fine-tuning, evaluations, and red-teaming. Candidates need a background in AI safety, strong Python and deep learning skills, and excellent communication.

Key Highlights

Conduct research to understand and shape how models handle harmful, sensitive, and dual-use requests.

Work across the full development stack, from pre-training data curation to safety evaluations and red-teaming.

Apply post-training techniques like RLHF/RLAIF and build safety evaluations for long-horizon and agentic tasks.

Competitive salary range of $350,000-$475,000, with visa sponsorship and relocation support.

Key Responsibilities

Build data filtering pipelines and quality classifiers to shape what models learn from pre-training corpora, and study downstream safety behavior.

Apply post-training techniques, including RL from human and AI feedback and policy-based reasoning, to shape how models handle harmful, sensitive, and dual-use requests.

Design, build, and maintain safety evaluations, focusing on model behavior in long-horizon and agentic tasks.

Generate and curate synthetic data to train and evaluate models on refusal boundaries and safety-relevant behaviors.

Red-team models and products to surface failure modes, jailbreaks, and emergent risks before deployment, and design mitigations.

Looking to advance your Machine Learning & AI career with relocation support? Explore Machine Learning & AI Jobs with Relocation Packages that include comprehensive packages to help you move and settle in your new role.

Technical Skills Required

Python Deep Learning AI Safety Research

Benefits & Perks

Health, dental, and vision insurance

Unlimited PTO

Paid parental leave

Visa sponsorship

Relocation support

Discover our full range of relocation jobs with comprehensive support packages to help you relocate and settle in your new location.

Nice to Have

Experience building evaluations for long-horizon, multi-step, or agentic tasks.

Experience generating synthetic data at scale for training or evaluation.

Experience with modern red-teaming/jailbreaking techniques.

Research contributions in AI safety, such as publications, open-source evaluations, or public red-teaming work.

Familiarity with the AI safety literature and current open problems (e.g., scalable oversight, reward hacking, jailbreak robustness).

PhD in Computer Science, Machine Learning, Physics, Mathematics, or equivalent industry research experience.

Job Description

About the Role

As a safety researcher, you'll work toward ensuring our models are safe and trustworthy. The role sits at the intersection of research and hands-on technical work. A central question is how models come to handle harmful or dual-use requests: what they learn from data, how training shapes where they refuse and where they engage, and what makes those boundaries reliable. You'll explore the science behind these behaviors and design experiments that inform how our models are trained and evaluated.

What You’ll Do

Want the full job description? Read the complete details on LinkedIn, the original posting.

Continue on LinkedIn

This is a short excerpt. All rights to the full description belong to its original publisher.