Member of Technical Staff - Safety

Own the red-teaming and adversarial evaluation pipeline for Reflection’s models, continuously probing for failure modes across security, misuse, and alignment gaps. Work hand-in-hand with the Alignment team to translate safety findings into concrete guardrails, ensuring models behave reliably under stress and adhere to deployment policies. Validate that every release meets the lab’s risk thresholds before it ships, serving as a critical gatekeeper for our open weight releases. Develop scalable, automated safety benchmarks that evolve alongside our model capabilities, moving beyond static datasets to dynamic adversarial testing. Research and implement state-of-the-art jailbreaking techniques and defenses to stay ahead of potential vulnerabilities in the wild.

Responsibilities

Own the red-teaming and adversarial evaluation pipeline for Reflection’s models, continuously probing for failure modes across security, misuse, and alignment gaps; Work hand-in-hand with the Alignment team to translate safety findings into concrete guardrails, ensuring models behave reliably under stress and adhere to deployment policies; Validate that every release meets the lab’s risk thresholds before it ships, serving as a critical gatekeeper for our open weight releases; Develop scalable, automated safety benchmarks that evolve alongside our model capabilities, moving beyond static datasets to dynamic adversarial testing; Research and implement state-of-the-art jailbreaking techniques and defenses to stay ahead of potential vulnerabilities in the wild.

Requirements

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; Thrive in a fast-paced, high-agency startup environment with bias toward action; Willing to make high-stakes decisions regarding model release and safety thresholds; Passionate about advancing the frontier of intelligence.

Nice to have

Experience with Reinforcement Learning (RLHF/RLAIF) and how it impacts model safety and alignment is a strong plus.

Benefits

Top-tier compensation (salary and equity); Stock options; Comprehensive medical, dental, vision, and life insurance with 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. and 30 days in the U.K.; Visa sponsorship and support for long-term immigration pathways; Regular off-sites, happy hours, and team celebrations.