LLM Safety Red Team Engineer

Sierra Ventures; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

Top-tier comp

Stock options

Healthcare coverage

Meals provided

Parental leave

Unlimited PTO

Visa sponsorship

Team events

Job summary

Reflection is seeking a safety-focused AI researcher to own red-teaming and adversarial evaluation for our models. You will translate safety findings into concrete guardrails with the Alignment team and validate releases against risk thresholds.

Ideal candidates have MS/PhD or equivalent in AI safety, deep LLM safety expertise, and strong software engineering skills to build automated evaluation pipelines. RLHF/RLAIF experience is a plus, and you should thrive in a fast-paced startup.

Qualifications

• MS or PhD in Computer Science, ML, or related field, or equivalent practical AI safety experience.
• Deep technical understanding of LLM safety, adversarial attacks, red-teaming, and interpretability.
• Strong software engineering experience with automated evaluation pipelines or large-scale ML systems.
• Experience with RLHF/RLAIF and its impact on safety and alignment is a plus.
• Comfort in a fast-paced startup with high ownership and action bias.
• Willingness to make high-stakes decisions on model releases and safety thresholds.

Responsibilities

• Own the red-teaming and adversarial evaluation pipeline for Reflection’s models, probing for failure modes across security, misuse, and alignment gaps.
• Collaborate with Alignment team to translate safety findings into guardrails for reliable model deployment.
• Serve as gatekeeper for releases to ensure risk thresholds are met before shipping open weights.
• Develop scalable, automated safety benchmarks that adapt to evolving model capabilities.
• Research and implement state-of-the-art jailbreaks and defenses to stay ahead of vulnerabilities.

Skills

LLM safety

Adversarial evaluation

Software engineering

Python

RLHF/RLAIF

Education

MS or PhD in CS/ML or equivalent

Tools

Python

TensorFlow/PyTorch

Job description

Reflection is seeking a safety-focused AI researcher to own red-teaming and adversarial evaluation for our models. You will translate safety findings into concrete guardrails with the Alignment team and validate releases against risk thresholds.

Ideal candidates have MS/PhD or equivalent in AI safety, deep LLM safety expertise, and strong software engineering skills to build automated evaluation pipelines. RLHF/RLAIF experience is a plus, and you should thrive in a fast-paced startup.