Remote Secure AI Research Engineer — LLM Safety

Brave; Greater London; Hybrid; GBP 90,000 - 150,000; Full time

Benefits offered by this job

Competitive compensation

International exposure

Room for growth

Remote or hybrid options

Job summary

Brave is seeking an AI Security Researcher / Research Engineer to help mitigate security risks in AI systems, especially LLM-powered web agents and chatbots. You will design secure-by-design architectures and audit Brave's AI products.

The role offers remote or hybrid work with London preferred, collaborating with privacy, ML, and cryptography researchers to shape Brave's security strategy for web agents and responsible releases.

Qualifications

• Demonstrated experience working on Secure AI (prompt injection attacks and security guardrails).
• Strong publication record in AI security, ML security, or closely related areas.
• Track record of shipping products in a fast-moving environment.
• Strong coding skills in Python and familiarity with ML frameworks like PyTorch or JAX.
• Experience training, fine-tuning, and evaluating large language models.
• Ph.D. in computer science preferred; exceptions possible with industry experience.

Responsibilities

• Design and execute adversarial evaluations to uncover failure modes in LLM-powered web agents and chatbots.
• Analyze model behavior to understand and forecast security risks in frontier models.
• Develop and prototype security-focused training and fine-tuning techniques.
• Augment web agents with security principles including information flow control and privilege control.
• Collaborate with engineers and researchers to translate findings into product changes and tests.
• Help define a forward-looking security strategy and policy for building and releasing web agents.

Skills

AI Security

Publications

Shipping products

Ambiguity handling

Security strategy

Education

PhD in Computer Science

Tools

Python

PyTorch

JAX

Job description

Brave is seeking an AI Security Researcher / Research Engineer to help mitigate security risks in AI systems, especially LLM-powered web agents and chatbots. You will design secure-by-design architectures and audit Brave's AI products.

The role offers remote or hybrid work with London preferred, collaborating with privacy, ML, and cryptography researchers to shape Brave's security strategy for web agents and responsible releases.