Staff AI Safety & Red-Team Lead

Methodfi; Greater London; On-site; GBP 75,000 - 95,000; Full time

Job summary

A leading AI research firm in Greater London is seeking a talented professional to own the red-teaming and adversarial evaluation pipeline for their models. This role involves ensuring model safety and compliance with deployment policies, crucial for successful releases. Ideal candidates will possess a graduate degree in Computer Science or a related field, deep understanding of LLM safety, and solid software engineering skills. The organization offers competitive compensation and extensive health benefits, fostering an impactful work environment.

Benefits

Top-tier compensation

Comprehensive health insurance

Paid parental leave

Daily lunches and dinners

Qualifications

• Deep technical understanding of LLM safety and adversarial attacks.
• Experience with automated evaluation pipelines and large-scale ML systems.
• Ability to make high-stakes decisions regarding model safety.

Responsibilities

• Own the red-teaming and adversarial evaluation pipeline for models.
• Work with Alignment team to implement safety findings.
• Validate releases meet risk thresholds before shipping.

Skills

LLM safety understanding

Software engineering

Automated evaluation pipelines

Reinforcement Learning

Education

Graduate degree in Computer Science or related discipline

Job description

A leading AI research firm in Greater London is seeking a talented professional to own the red-teaming and adversarial evaluation pipeline for their models. This role involves ensuring model safety and compliance with deployment policies, crucial for successful releases. Ideal candidates will possess a graduate degree in Computer Science or a related field, deep understanding of LLM safety, and solid software engineering skills. The organization offers competitive compensation and extensive health benefits, fostering an impactful work environment.