Member of Technical Staff - Safety Lead
Reflection7 months ago
Responsibilities
- Own the red-teaming and adversarial evaluation pipeline for Reflection’s models across security, misuse, and alignment failure modes.
- Collaborate with the Alignment team to translate safety findings into concrete guardrails and deployment policies.
- Validate that model releases meet the lab’s risk thresholds before shipping.
- Develop scalable automated safety benchmarks using dynamic adversarial testing.
- Research and implement state-of-the-art jailbreaking techniques and defenses.
Requirements
- Graduate degree (MS or PhD) in Computer Science, Machine Learning, or a related discipline, or equivalent practical experience in AI Safety.
- Deep technical understanding of LLM safety, adversarial attacks, red-teaming methodologies, and interpretability.
- Strong software engineering capabilities and experience building automated evaluation pipelines or large-scale ML systems.
- Experience with Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning from AI Feedback (RLAIF) is a strong plus.
- Ability to make high-stakes decisions regarding model releases and safety thresholds.
Benefits
- Top-tier compensation with salary and equity structured to recognize and retain talent globally.
- Comprehensive medical, dental, vision, life, and disability insurance.
- Fully paid parental leave for all new parents, including adoptive and surrogate journeys.
- Financial support for family planning.
- Paid time off and relocation support.
- Daily lunch and dinner, regular off-sites, and team celebrations.
Categories
AI ResearchTesting
About Reflection
Reflection is a research lab making intelligence open and accessible for everyone to use, customize, and build on. Our team previously built frontier LLMs at labs like DeepMind, OpenAI, and Anthropic. We believe AI should be built in the open, with transparent research and collaborative development. That means giving enterprises, governments, and sovereign entities true ownership and control of AI that performs at the highest level. Our mission: make intelligence open and accessible to all.