AI Security Researcher/Research Engineer

Brave
London
Workplace: HybridFull timeFunction: Research & Scientific (R&D)Skills: ["Ownership","Problem-solving","Collaboration","Clarity"]

Design and implement secure-by-design architectures for Brave’s LLM-powered web agents and chatbots. Conduct adversarial evaluations (e.g., prompt injection, tool abuse, data exfiltration), analyze model behavior to anticipate frontier-model risks, and prototype security-focused training and fine-tuning approaches. Partner with engineers and research teams to turn findings into product changes, tests, and measurable security improvements while shaping Brave’s forward-looking security strategy and policy for responsibly releasing web agents.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Brave
Brave
2 days ago

AI Security Researcher/Research Engineer

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 7 hours agoStatus: Live

Job Summary

Design and implement secure-by-design architectures for Brave’s LLM-powered web agents and chatbots. Conduct adversarial evaluations (e.g., prompt injection, tool abuse, data exfiltration), analyze model behavior to anticipate frontier-model risks, and prototype security-focused training and fine-tuning approaches. Partner with engineers and research teams to turn findings into product changes, tests, and measurable security improvements while shaping Brave’s forward-looking security strategy and policy for responsibly releasing web agents.
Location: London
Workplace: Hybrid
Employment Type: Full time
Job Function: Research & Scientific (R&D)

Key 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 such as information flow control, privilege control, and contextual security.
  • •Partner with engineers and privacy/ML/cryptographic researchers to translate findings into product changes, tests, and measurable improvements.

Key Requirements

  • •Demonstrated experience working on secure AI, including prompt injection attacks and security guardrails.
  • •Strong publication record in AI security, ML security, or closely related areas.
  • •Track record of shipping products and features 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.
Experience:AI securityML securityMachine learningLarge language modelsWeb agentsOpen source
Education:
Skills:OwnershipProblem-solvingCollaborationClarity
Languages:English
Tech Stack:PythonPyTorchJAXLLMLarge language modelsWeb agentsZKPSMPCConfidential computing

Company Brief

Brave
Develops the Brave web browser and privacy-focused web technologies that block trackers and ads by default, offering faster browsing, optional privacy-preserving ad and reward systems (BAT) and related products for users and publishers.
Industry: Cybersecurity
Company Size: Large (251 to 1,000 employees)
Growth: Established Company
Headquarters: San Francisco, United States
Founded: 2015
WebsiteLinkedIn