Member of Technical Staff – Safety

About the role

Join Reflection’s research lab to own the red‑teaming and adversarial evaluation pipeline for our open models. You will continuously probe for failure modes across security, misuse, and alignment gaps, ensuring safe releases.

Key responsibilities

• Own the red‑teaming pipeline, identifying security, misuse, and alignment failures.
• Collaborate with the Alignment team to translate safety findings into guardrails and deployment policies.
• Validate each model release against risk thresholds as a gatekeeper for open‑weight releases.
• Develop scalable, automated safety benchmarks and dynamic adversarial testing.
• Research and implement state‑of‑the‑art jailbreaking techniques and defenses.

Required profile

• Graduate degree (MS or PhD) in Computer Science, Machine Learning, or related field, or equivalent practical AI safety experience.
• Deep technical understanding of LLM safety, adversarial attacks, red‑teaming, and interpretability.
• Strong software engineering background building automated evaluation pipelines or large‑scale ML systems.
• Experience with reinforcement learning (RLHF/RLAIF) is a strong plus.
• Ability to thrive in a fast‑paced, high‑agency startup environment and make high‑stakes release decisions.

Required skills

• Adversarial attack techniques
• Red‑teaming methodologies
• Model interpretability
• Automated evaluation pipeline development
• Large‑scale machine‑learning system engineering
• Reinforcement learning (RLHF/RLAIF)

What we offer

• Top‑tier compensation: salary and equity
• Stock options for all contributors
• Comprehensive health, dental, vision, and life coverage plus wellness allowance
• Daily lunch and dinner provided on‑site
• 22 weeks paid parental leave for all new parents
• Unlimited PTO in the U.S. (30 days in the U.K.)
• Visa sponsorship and immigration support
• Regular off‑sites, happy hours, and team celebrations