Backend Engineer (AI Agent)

About the role

Our client is creating a proactive AI chat application that brings intelligence to everyday conversations, errands, and workflows. As a Backend Engineer you will own the inference and orchestration layer that powers every AI interaction, ensuring low latency, high reliability, and cost‑effective operation.

Key responsibilities

• Build and operate production‑grade backend systems that deliver AI‑powered features to mobile and desktop clients.
• Design inference pipelines, orchestration layers, and clear service boundaries around large language models and multimodal components.
• Own production concerns such as monitoring, logging, alerting, and incident response.
• Optimize latency and throughput through caching, batching, streaming, and efficient resource utilization.

Required profile

• Strong fundamentals in backend engineering within production environments.
• Experience delivering high‑throughput, low‑latency services.
• Familiarity with AI inference patterns (LLMs, embeddings, multimodal data).
• Comfortable debugging distributed systems under load.
• Bias toward shipping code and learning from real‑world behavior.

Required skills

• Python
• NodeJs
• PyTorch
• OpenAI / Anthropic / open‑source LLMs
• SQL & NoSQL databases
• Kubernetes
• Docker