Member of Technical Staff - Safety

The role

This person will own the red-teaming and adversarial evaluation pipeline for Reflection's models. They will work with the Alignment team to translate safety findings into guardrails and develop automated safety benchmarks.

What you will do

• Own the red-teaming and adversarial evaluation pipeline for Reflection's models.
• Work with the Alignment team to translate safety findings into concrete guardrails.
• Validate that every release meets the lab's risk thresholds.
• Develop scalable, automated safety benchmarks.
• Research and implement state-of-the-art jailbreaking techniques and defenses.

Required qualifications

• Graduate degree (MS or PhD) in Computer Science, Machine Learning, or related discipline, or equivalent practical experience in AI Safety.
• Deep technical understanding of LLM safety, including adversarial attacks, red-teaming methodologies, and interpretability.
• Strong software engineering capabilities with experience building automated evaluation pipelines or large-scale ML systems.
• Willing to make high-stakes decisions regarding model release and safety thresholds.

Nice to have

• Experience with Reinforcement Learning (RLHF/RLAIF) and how it impacts model safety and alignment

Benefits

• Salary and equity
• Stock options
• Comprehensive medical, dental, vision, and life
• Annual wellness allowance
• Lunch and dinner provided in the office daily
• 22 weeks paid parental leave for all new birthing and non-birthing parents, including adoptive and surrogate journeys
• Unlimited paid time off in the U.S.
• 30 days paid time off in the U.K.
• Sponsorship support for visas
• Regular off-sites, happy hours, and team celebrations

Before you apply

• This position may require access to technology or source code subject to the U.S. Export Administration Regulations.
• Any offer of employment may be conditioned on the Company's ability to provide access to technology or source code in compliance with U.S. export control laws.

About the company

Reflection is a research lab making intelligence open and accessible for everyone to use, customize, and build on. They build open models that let anyone control their intelligence and help shape the future of AI.