Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
84
Хорошая вакансия
развернуть
Чётко очерченная дипломная работа сочетает практическую кибербезопасность с LLM-агентами, но требования к выпуску, языкам и работе в офисе заметно сужают круг подходящих участников.
Жёсткие условия
Чёткая тема
Перспективная тема
?Работа в офисе
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Thesis: Hack Yourself First: Autonomous LLM Agents for Continuous Penetration Testing (Cybersecurity): Evaluating an LLM agent that performs reconnaissance, vulnerability discovery, exploitation, and security reporting in an authorised test network with an accent on continuous penetration testing and reliable findings. Focus on measuring vulnerability coverage and execution time, validating reports through multi-agent orchestration, and assessing agent safety through sandboxing or cloned environments.
Location: Onsite at the office in Sundsvall, Sweden. Start date: January or March 2027.
Company
hirify.global is a strategic partner in product and digital service development, combining cross-functional expertise to deliver solutions from idea to completion.
What you will do
Evaluate an LLM agent that performs continuous penetration testing in a test environment with known vulnerabilities.
Run the agent from a single jump host to perform reconnaissance, port scanning, vulnerability discovery, exploitation, and reporting.
Compare generated reports with known vulnerabilities and measure findings, exploitation results, and execution time.
Investigate report reliability, false positives, and the use of multi-agent orchestration for verification.
Assess trust and safety risks, including whether cloned environments or sandboxing reduce the risk of damaging systems.
Requirements
Bachelor’s or Master’s degree in Computer Science, Computer Engineering, or a related field.
Graduation in June 2027.
Fluency in Swedish, written and spoken.
Fluency in English, written and spoken.
Testing must be limited to authorised targets with a defined threat model.
The work uses existing models; training new models is out of scope, and fine-tuning is considered only with a clear justification.
The proof-of-concept agent only needs to identify known vulnerabilities and common weaknesses; zero-day research is out of scope.
Nice to have
Interest in cybersecurity and artificial intelligence.
Familiarity with MCP, Linux, Nmap, weak or default credentials, network segmentation, misconfigurations, or OWASP Top 10 web vulnerabilities.
Culture & Benefits
Thesis work with hands-on experience on real projects.
Supportive and innovative working environment.
Proof-of-concept research intended for experimentation and evaluation, with potential for later development into a business solution.
Applications are accepted through the careers page only due to GDPR.
Hiring process
Submit the application through the careers page as soon as possible and no later than 30 November 2026.
Questions may be sent to johanna.edstrom@knightec.se.
Будьте осторожны
Если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого. Это мошенники. Обязательно жмите «Пожаловаться» или пишите в поддержку. Подробнее в гайде →