Backend Engineer, AI Systems

About the role

We are building a proactive smart assistant that brings intelligence to everyday conversations, errands, and workflows. As a Backend Engineer, AI, 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 backend systems that serve AI‑powered features across mobile and desktop clients.
• Design inference pipelines and orchestration layers for multi‑step workflows, tool calls, and retries.
• Manage the full lifecycle of AI requests, including routing, caching, batching, streaming, and state management.
• Optimize latency, throughput, and cost for model inference and downstream services.
• Implement observability (logging, tracing, debugging) for AI outputs and failures.
• Collaborate with ML and product teams to translate model capabilities into stable, production‑grade APIs.

Required profile

• Strong backend engineering fundamentals in production environments.
• Experience running high‑throughput, low‑latency services.
• Familiarity with AI inference patterns such as LLMs, embeddings, and multimodal models.
• Comfortable debugging distributed systems under load.
• Bias toward shipping and learning from production behavior.

Required skills

• Python
• Node.js
• PyTorch
• OpenAI / Anthropic / open‑source LLM APIs
• SQL & NoSQL databases
• Kubernetes
• Docker