Backend Engineer, AI (Agent Systems)

Overview

Own the inference and orchestration layer for AI interactions, building production backend systems that deliver fast, reliable, observable APIs.

What you'll do

• Build backend systems serving AI-powered production features.
• Design inference pipelines and model orchestration layers.
• Define service boundaries around AI models.
• Monitor, log, alert on, and respond to production incidents.
• Optimize latency and throughput across inference, caching, batching, and streaming.

What you'll need

• Strong backend engineering fundamentals in production environments.
• Experience running high-throughput, low-latency services.
• Familiarity with AI inference patterns, including LLMs, embeddings, and multimodal systems.
• Ability to debug distributed systems under load.
• Experience or proficiency with Python.
• Experience or proficiency with Node.js.
• Familiarity with PyTorch, LLMs, SQL and NoSQL, Kubernetes, and Docker.

Details

• Location: United States.
• Interviews may be conducted virtually and/or onsite.
• The process includes three to four interviews.