Generative AI Engineer

Accelerate Your Career in Cybersecurity

Join Pentera and take your career to the next level in cybersecurity. As a leader in Automated Security Validation, we help businesses around the world safely emulate real-world attacks to uncover their vulnerabilities. At Pentera, you'll be at the forefront of cybersecurity innovation, working on advanced AI-driven tools that revolutionize security testing through conversational interfaces and intelligent automation.

With over 350 team members and 1,000+ customers in more than 50 countries, Pentera is a growing company supported by top investors like Insight Partners, K1, and The Blackstone Group.

If you're looking to grow your skills, make a difference, and be part of an innovative team building the future of AI-powered cybersecurity, Pentera is the place for you.

About The Role

We are seeking a highly skilled and experienced Generative AI (GenAI) Engineer to join our team at Pentera. In this role, you will be instrumental in building and advancing our AI-driven cybersecurity testing platform, focusing on agentic flows and conversational AI interfaces that transform how security professionals interact with automated penetration testing tools.

You will work on cutting-edge AI technologies to implement our vision, where natural language conversations drive sophisticated adversarial testing scenarios. Your work will directly contribute to making cybersecurity testing more accessible, intelligent, and adaptable through multi-agent orchestration, real-time decision making, and contextual understanding of complex security environments.

As part of our team, you'll collaborate with top-tier professionals in both AI and cybersecurity domains, helping to evolve our platform into the next generation of conversational, AI-powered security validation tools.

Roles And Responsibilities

• Design and develop agentic AI systems (LangGraph/LangChain in Python or Spring AI in Java) for multi-step security workflows.
• Build conversational AI interfaces that convert natural language into executable attack scenarios.
• Implement AI-powered web testing for vulnerability discovery.
• Develop RAG systems and multi-agent orchestration by utilizing vector stores and integrating with foundation models using AWS Bedrock.
• Ensure safe, reliable AI testing with guardrails, evaluation, and clean, documented code.
• Take end-to-end responsibility for AI system development, from research and prototyping through deployment and monitoring in production environments.
• Stay updated with the latest advancements in generative AI, agentic systems, and cybersecurity AI applications, bringing fresh ideas and cutting-edge techniques to enhance our platform capabilities.
  
  

• 5+ years of backend engineering experience, with emphasis on Python (preferred) and optionally Java
• Extensive experience with LangGraph and LangChain frameworks for building agentic AI systems and multi-agent orchestration.
• Experience with Large Language Models (LLMs), including prompt engineering, RAG implementations, and model evaluation techniques.
• Knowledge of multi-agent systems, including agent communication patterns, task decomposition, hierarchical planning, and collaborative problem-solving architectures.
• Experience designing RESTful APIs for service integration and microservices.
• Experience with relational and non-relational databases (preferably MongoDB and PostgreSQL) for managing AI-related data.
• Experience with vector databases and semantic search technologies for knowledge retrieval and context augmentation.
• Experience with containerization (Docker) and cloud-native deployment patterns for AI applications.
• B.Sc. in Computer Science, AI/ML, or related field
  
  

• Experience with AWS Bedrock and AWS AI services, including model integration, customisation, and serverless deployment.
• Cybersecurity knowledge, including an understanding of penetration testing concepts, security vulnerabilities, and attack methodologies