SonarSource Sàrl
Senior AI Engineer
📍 Geneva
Role and responsibilities
Design & Develop: Architect and implement end-to-end AI Agents and full-stack applications that automate complex business processes. Foundational Engineering: Build and maintain the core AI tech stack, including agent orchestration frameworks, vector database integrations, and RAG (Retrieval-Augmented Generation) pipelines. Cloud Orchestration: Oversee the deployment and management of scalable AI services, selecting and adapting infrastructure to meet stringent requirements for high availability, performance, and efficiency. Strategic Transformation: Act as a key contributor to Sonar’s AI transformation, identifying high-impact opportunities for agentic automation across different departments. Governance & Ethics: Collaborate with cross-functional teams to establish governance, security protocols, and best practices for AI development and data privacy. Full-Stack Ownership: Manage the entire lifecycle of internal tools, from backend logic and LLM prompt engineering to intuitive frontend interfaces for internal users.
Team / description
Sonar is driving the future of agent-centric software development. As the leader in AI code review and verification, we solve a critical problem: ensuring that software generated by AI-assisted developers or autonomous agents is reliable, secure, and maintainable. Our team operates across global hubs in Austin, Bochum, Dubai, Geneva, London, Singapore, Tokyo, and Washington D.C. We move with a mindset we call CODE: Committed to our customers and community, Obsessed with quality, Deliberate in our decisions, Effective as one team.
Qualifications and Skills
Full-Stack Expertise: Professional experience in full-stack development (e.g., Python, Node.js, React, or similar modern stacks).
AI Agent Mastery: Proven experience developing and deploying autonomous AI Agents using frameworks such as LangChain, AutoGen, CrewAI, or similar.
Automation Roots: A strong background in traditional automation development (e.g., scripting, workflow engines, or RPA) prior to the LLM era, demonstrating a deep understanding of logic-based systems.
Cloud Proficiency: Hands-on experience architecting and deploying production-grade applications on any major cloud platform (AWS experience is highly recommended).
Architectural Vision: Deep understanding of the specific architectures required for agentic workflows, including state management, tool-calling, and memory systems.
Data & AI Skills: Experience with vector databases (e.g., Pinecone, Weaviate), fine-tuning (optional but preferred), and advanced prompt engineering.
Collaborative Mindset: Ability to work with non-technical stakeholders to define governance and translate business needs into technical requirements.
Growth Mindset: A passion for staying at the forefront of AI research and a desire to continuously evolve your skill set.