Backend Engineer, AI (Agent Systems)

About this role

A1 is seeking a Backend Engineer to build and operate the inference and orchestration systems powering their AI smart assistant. You'll design production-grade pipelines that handle multi-step reasoning, external tool integration, and reliable long-running workflows while optimizing for latency, correctness, and cost.

What you'll do

• Build and operate backend systems serving AI-powered features in production
• Design inference pipelines, orchestration layers, and service boundaries around LLM models
• Own production concerns including monitoring, logging, alerting, and incident response
• Optimize latency and throughput across inference, caching, batching, and streaming
• Debug and troubleshoot distributed systems under load
• Iterate on system performance based on real production usage patterns

What they're looking for

• Strong backend engineering fundamentals in production environments
• High-throughput, low-latency service design and operation
• AI inference patterns (LLMs, embeddings, multimodal models)
• Python and/or Node.js
• Kubernetes and Docker containerization
• SQL and NoSQL databases
• Distributed systems debugging
• Production monitoring and observability tools

Benefits

• Work on a small, world-class team with high talent density
• Located in Zurich, Switzerland
• Opportunity to ship impactful AI products used by millions
• Rapid decision-making environment with collective ownership
• Balanced approach between shipping quality work and learning