Open-Model AI Safety Lead: Red Team & Validation | Equity

Reflection AI; Greater London; On-site; GBP 100,000 - 180,000; Full time

Benefits offered by this job

Top-tier compensation

Comprehensive medical, dental, and vision insurance

Paid parental leave for all new parents

Paid time off

Daily lunch and dinner provided

Job summary

A cutting-edge AI company in Greater London is seeking an individual with a graduate degree in Computer Science or related fields to lead the red-teaming and adversarial evaluation of their models. The role requires a deep understanding of LLM safety, strong software engineering skills, and experience with Reinforcement Learning. Ideal candidates thrive in a dynamic environment and are passionate about AI advancements. This position offers competitive compensation and comprehensive health benefits.

Qualifications

• Graduate degree (MS or PhD) in Computer Science, Machine Learning, or equivalent practical experience in AI Safety.
• Strong software engineering capabilities with experience building automated evaluation pipelines or large-scale ML systems.
• Experience with Reinforcement Learning (RLHF/RLAIF) and how it impacts model safety.

Responsibilities

• Own the red-teaming and adversarial evaluation pipeline for models.
• Work with the Alignment team to ensure models behave reliably under stress.
• Develop scalable, automated safety benchmarks for model evaluation.

Skills

Deep technical understanding of LLM safety

Software engineering capabilities

Experience with Reinforcement Learning

Adversarial attacks knowledge

Education

Graduate degree in Computer Science or related discipline

Job description

A cutting-edge AI company in Greater London is seeking an individual with a graduate degree in Computer Science or related fields to lead the red-teaming and adversarial evaluation of their models. The role requires a deep understanding of LLM safety, strong software engineering skills, and experience with Reinforcement Learning. Ideal candidates thrive in a dynamic environment and are passionate about AI advancements. This position offers competitive compensation and comprehensive health benefits.