AI Systems / Context Engineer

About Virtido

Virtido is an entrepreneurial and innovative IT company headquartered in Zurich, Switzerland. We realize ideas and projects - from strategic concept to technical implementation closely alongside our dynamic clients with a strong focus on start-up or fast-growing companies. Since inception in 2015, we have grown rapidly to currently 140+ professionals in Switzerland, Poland, Ukraine and the Philippines.

About the client

A fast-growing cybersecurity consultancy focused on helping startups and SMEs secure their digital infrastructure without requiring large internal security teams or excessive investment. The company provides pentesting, security audits, and tailored micro-consulting services designed specifically for scaling technology businesses.

In addition, the company develops an innovative proprietary platform that transforms how organizations approach cybersecurity by automating critical security tasks such as vulnerability detection, phishing analysis, and technical reporting through low-code workflows and AI-powered automation.

About the role

We are looking for an experienced AI Systems Engineer (also referred to as a Context Engineer) to join an innovative cybersecurity and AI-driven technology environment. This is a project-based role (1-2 months of engagement) focuses on designing, optimizing, and maintaining advanced AI systems with a strong emphasis on context management, memory optimization, orchestration workflows, and scalable AI architecture.

The ideal candidate combines hands-on engineering expertise with a deep understanding of how modern AI systems process, retain, retrieve, and utilize contextual information across complex workflows and autonomous agents.

Responsibilities

• Design and optimize AI system architectures and orchestration workflows
• Manage AI memory systems, contextual retrieval pipelines, and state handling
• Improve LLM performance through prompt engineering, context optimization, and workflow tuning
• Develop scalable AI automation pipelines and agent-based systems
• Design and maintain RAG (Retrieval-Augmented Generation) systems
• Optimize token usage, latency, and inference efficiency
• Build integrations between AI systems, APIs, databases, and low-code automation platforms
• Implement monitoring, evaluation, and testing frameworks for AI reliability and quality
• Collaborate with cybersecurity and engineering teams to ensure secure AI implementations

Requirements

• Strong experience with AI systems engineering and LLM-based applications
• Experience designing AI agent workflows and orchestration systems
• Understanding of AI memory management, context windows, embeddings, and vector databases
• Experience with RAG architectures and semantic retrieval systems
• Strong programming skills in Python
• Experience with APIs, automation frameworks, and low-code workflows
• Familiarity with frameworks such as LangChain, LlamaIndex, AutoGen, CrewAI, or similar
• Experience working with vector databases such as Pinecone, Weaviate, ChromaDB, or FAISS
• Understanding of prompt engineering and LLM optimization techniques
• Knowledge of cloud environments and scalable system design
• Good level of English (B2+)