Staff Backend Engineer, AI Platform

This position is posted by Jobgether on behalf of a partner company. We are currently looking for a Staff Backend Engineer, AI Platform in Switzerland.

This role sits at the core of a next-generation AI initiative, responsible for building the foundational platform that powers all AI-driven features across a large-scale product ecosystem. You will design and lead the architecture of a multi-agent AI system, enabling teams to safely and reliably deploy production-grade AI capabilities. The scope of your work spans orchestration, LLM integration, evaluation frameworks, and observability systems that ensure performance and trust at scale. You will operate in a high-autonomy environment, working closely with engineering leadership and cross-functional teams to define how AI is built, shipped, and monitored. This is a deeply technical and strategic role with direct impact on thousands of end users and the company’s AI future. You will be joining a fast-scaling, remote-first engineering culture where ownership and innovation are central.

• Own the architecture and technical vision of the AI Platform, including multi-agent orchestration, LLM gateway, evaluation systems, and observability infrastructure.
• Design and build production-grade AI services that enable scalable, reliable, and safe deployment of AI features across the organization.
• Establish evaluation frameworks, quality gates, and testing systems for prompts and AI workflows, ensuring measurable confidence in production AI systems.
• Define and evolve LLM gateway capabilities including routing, failover, cost tracking, and rate limiting.
• Drive cross-team adoption by creating integration standards, internal documentation, and reusable blueprints for AI development.
• Influence engineering-wide practices around prompt engineering, agent design, testing, and observability.
• Mentor engineers and elevate technical standards through code reviews, design discussions, and hands-on collaboration.

Requirements:

• 8+ years of software engineering experience, including at least 2 years in a Staff or equivalent senior technical role.
• Strong Python expertise with experience building and maintaining production-grade backend services.
• Proven experience designing, shipping, and operating LLM-based or AI-powered systems in production environments.
• Strong system design skills with the ability to build scalable, maintainable, and extensible architectures.
• Familiarity with modern AI tooling ecosystems such as LangChain, LangGraph, LiteLLM, Langfuse, Phoenix, MLflow, or similar.
• Experience or strong exposure to multi-agent systems, including orchestration, tool calling, and context management (strong plus).
• Comfort working across heterogeneous environments including Python, Go, PHP, and frontend systems.
• Strong infrastructure knowledge with AWS, Kubernetes, and CI/CD pipelines.
• Excellent communication and influence skills, with the ability to drive adoption across multiple engineering teams.

Benefits:

• Competitive salary aligned with market standards in the applicant’s location.
• Fully remote work within the country of residence, offering maximum flexibility.
• Equity and stock options in a fast-growing, profitable company.
• Strong focus on professional development and long-term career growth.
• Annual paid leave aligned with local regulations.
• Country-specific benefits such as private healthcare and pension contributions where applicable.
• Inclusive and global team culture spanning 40+ countries.
• Values-driven environment with high autonomy and ownership from day one.