LLM Security Researcher

Helsinki, Finland

Huawei Finland R&D

Huawei is a leading global provider of information and communications technology (ICT) infrastructure and smart devices.

View all jobs at Huawei Finland R&D

Apply now Apply later

Huawei Consumer Business Group is the leader in the all-scenario AI life. It covers smartphones, PCs and tablets, wearables, mobile broadband devices, family devices and device cloud services. Huawei Consumer Business Group is dedicated to delivering the latest technologies to consumers and sharing the happiness of technological advances with more people around the world.

Content Security Lab in Helsinki Research Center’s mission is to advance technology to protect the online safety of Huawei mobile users. We are seeking a highly skilled AI researcher to join our team and work on cutting-edge research in LLM security. As an LLM Security AI Agent, you will be responsible for developing innovative techniques to mitigate the risks associated with large language models (LLMs). This includes developing methods to detect and prevent jailbreaking attacks, backdoor attacks, and other malicious activities.

Location: This position is located at our R&D office in Ruoholahti, Helsinki, Finland.

This is a full-time consultant position. The consultant shall be employed by Huawei's supplier.


Responsibilities

  • Conduct advanced research in LLM security, focusing on areas such as adversarial attacks, model robustness, and privacy preservation.
  • Develop robust techniques to prevent malicious users from exploiting LLMs to generate harmful content.
  • Design effective algorithms to identify and eliminate hidden backdoors in LLMs.
  • Work on securing LLM-powered agents, such as SeeAct, from malicious attacks and manipulation.
  • Develop rigorous evaluation methodologies to assess the effectiveness of security techniques.
  • Collaborate with cross-functional teams to integrate security solutions into LLM products.
  • Publish research papers in top-tier conferences and journals.
  • Provide technology insights and contribute to the development of the Content Security Research Roadmap.
  • Propose research topics and prepare research proposals for state-of-the-art research on AI Security & Safety topics.
  • Conduct state-of-the-art research on AI Security & Safety topics.
  • Assess the technology advancement and novelty of research proposals and provide technical assessment reports.
  • Provide technical guidance to internal and university collaborators' expert teams on solutions' architecture and design.
  • Report and present findings and solutions to internal stakeholders and external audiences with effective written and verbal communication.

  • Requirements:

  • Ph.D. in Computer Science, Machine Learning, or a related field.
  • Strong theoretical foundation in machine learning, deep learning, and natural language processing.
  • Hands-on experience with large language models and deep learning frameworks (e.g., PyTorch, TensorFlow).
  • Proficiency in Python programming and data analysis tools.
  • Excellent problem-solving and analytical skills.
  • Strong communication and collaboration skills.
  • Experience with security-related research, such as adversarial attacks, is a plus.

  • What We Offer:

    • Opportunity to work on cutting-edge research in LLM security.
    • Competitive salary and benefits package.
    • Collaborative and supportive work environment.
    • Access to state-of-the-art computing resources.


    Apply now Apply later

    * Salary range is an estimate based on our InfoSec / Cybersecurity Salary Index 💰

    Job stats:  0  0  0
    Category: Research Jobs

    Tags: Cloud Computer Science LLMs Machine Learning NLP Privacy Python R&D

    Perks/benefits: Career development Competitive pay Conferences

    Region: Europe
    Country: Finland

    More jobs like this

    Explore more career opportunities

    Find even more open roles below ordered by popularity of job title or skills/products/technologies used.