• You'll build and own the AI systems that make Live Breach feel like a real incident rather than a scripted exercise. • The AI attacker agent - an autonomous LLM-powered agent that receives a threat actor profile, a network briefing, and a configured attack chain, then executes it against a live environment. • The exercise orchestration layer - a parallel system that monitors the network during a live exercise, recognises which attack techniques have executed, listens for correct containment and eradication actions from participants, and surfaces investigation tasks tied to real attacker behaviour. • Prompt engineering for both red and blue team agent components, in close collaboration with our content engineering team • Integration with adversary emulation tooling for realistic technique execution • User emulation and noise generation — simulating realistic background activity so participants must distinguish real attacker behaviour from normal log volume • Documentation and architecture that allows the broader engineering team to operate and debug the AI layer without dependency on any single person.

• Design and develop agentic AI systems that can retrieve relevant information and interact with tools and services to support and automate operational workflows in cloud environments • Design and implement agentic AI systems capable of reasoning, planning, and executing tasks across complex operational environments • Develop AI agents that can interact with tools and services, including APIs, monitoring systems, knowledge bases, and operational platforms • Build mechanisms for context and knowledge retrieval, enabling agents to access documentation, historical data, and structured information required for decision-making • Implement autonomous or semi-autonomous workflows where AI agents assist humans by analysing situations, proposing actions, and executing tasks where appropriate • Develop scalable backend services and interfaces that allow agents to interact with enterprise systems and cloud platforms • Deploy and operate agent-based solutions in cloud-native environments, ensuring reliability, observability, and maintainability

Role Description We are seeking a talented and motivated Senior AI Engineer to join our team. The person will play a key role in designing, implementing, and maintaining AI solutions that create business value and enhance user experiences. - Design and develop agentic AI systems that can retrieve relevant information and interact with tools and services to support and automate operational workflows in cloud environments. - Design and implement agentic AI systems capable of reasoning, planning, and executing tasks across complex operational environments. - Develop AI agents that can interact with tools and services, including APIs, monitoring systems, knowledge bases, and operational platforms. - Build mechanisms for context and knowledge retrieval, enabling agents to access documentation, historical data, and structured information required for decision-making. - Implement autonomous or semi-autonomous workflows where AI agents assist humans by analysing situations, proposing actions, and executing tasks where appropriate. - Develop scalable backend services and interfaces that allow agents to interact with enterprise systems and cloud platforms. - Deploy and operate agent-based solutions in cloud-native environments, ensuring reliability, observability, and maintainability. Qualifications - Bachelor’s or Master’s in Computer Science or an equivalent field. - 5+ years of professional experience with Python programming language. - Experience with building REST APIs and backend services. - Extensive experience in the full software development life cycle, from design and implementation to testing and deployment. - Experience building LLM (Large Language Models) - based applications and agent workflows. - Prompt engineering and tool integration. - Experience with RAG, context management and vector databases. - Practical understanding of security and safety in agent systems (prompt injection, data privacy, least-privilege tool access). - Experience in using Git in a professional/business environment. - Ability to communicate clearly and concisely about complex technical, organizational and/or architectural challenges and propose iterative solutions. - Experience working in Agile/Scrum environments. - Proficiency in written and spoken English. Requirements - Familiarity with MCP or A2A communication. Benefits - A warm and supportive work environment where you can reach your full potential. - Flexible working hours that allow you to balance your work and personal life. - Unlimited home office to help you stay productive and focused. - Opportunities for professional development, including certifications and training. - Additional benefits for academic teaching and speaking engagements. - Knowledge-sharing sessions where you can learn from our Dreamix team. - Team and company-wide events that bring us together. - Amazing week-long summer office and winter office initiatives. - Additional health insurance and dental allowance to ensure your well-being. - Multisport card to encourage a healthy and active lifestyle. - Office massages to help you relax and unwind.

• Design and build agentic systems: single agents, multi-agent orchestration, and sub-agent patterns for complex workflows (planner/executor, supervisor/worker, hierarchical task decomposition) • Develop MCP (Model Context Protocol) servers and tools that expose internal systems, datasets, and actions to LLM-powered applications in a safe, governed, and reusable way • Implement retrieval systems (RAG, hybrid search, graph-based retrieval) including chunking, embedding, re-ranking, and context-assembly strategies • Build and maintain MLOps automation: CI/CD for models and agents, environment management, artifact handling, and versioning of prompts, models, data, and code • Implement observability for AI systems: tracing, token/latency/cost metrics, quality and drift monitoring, alerting, and incident response • Build and maintain data pipelines for ingestion, transformation, and export across multiple sources and destinations • Expose well-modelled, governed datasets and APIs that agents, tools, and downstream consumers can rely on • Ensure secure data handling and compliance with relevant data protection standards and internal policies • Contribute to documentation, standards, and continuous improvement of the data platform and engineering processes