Full Stack Engineer, AI systems

About this role

A1 seeks a Full Stack Engineer to build production-grade backend systems powering an AI-driven smart assistant. You'll design inference pipelines, ensure reliability at scale, and own production concerns like monitoring and incident response for systems handling multi-step AI workflows.

What you'll do

• Build and operate backend systems serving AI features in production environments
• Design inference pipelines, orchestration layers, and service boundaries around LLMs
• Implement monitoring, logging, alerting, and incident response infrastructure
• Optimize latency and throughput across inference, caching, batching, and streaming
• Debug and resolve distributed systems issues under load
• Collaborate on stable API design integrating frontend and ML components

What they're looking for

• Backend engineering in production environments
• High-throughput, low-latency service design
• AI inference patterns (LLMs, embeddings, multimodal models)
• Python and Node.js
• Kubernetes and Docker
• SQL and NoSQL databases
• Distributed systems debugging
• Monitoring and observability tools