Backend Engineer, AI Systems — Scalable Inference & Pipelines

ActAI; Zürich; Vor Ort; CHF 120.000 - 180.000; Vollzeit

Zusammenfassung

ActAI is building reliable AI-powered workflows and APIs that scale. We seek a Backend Engineer, AI who owns inference and orchestration between models and users, delivering fast, stable, observable APIs used across clients.

You will collaborate with ML and product teams to translate model capabilities into production-grade systems, focusing on latency, reliability and cost, with production-grade tooling and observability.

Qualifikationen

• Experience running high-throughput, low-latency services.
• Familiarity with AI inference patterns (LLMs, embeddings, multimodal).
• Bias toward shipping and learning from production behavior.

Aufgaben

• Own the inference and orchestration layer powering AI interactions.
• Build and operate production systems turning model capability into fast, stable APIs.
• Design inference pipelines and orchestration layers for multi-step workflows, tool calls, and retries.
• Manage routing, caching, batching, streaming, and state management of AI requests.
• Optimize latency, throughput, and cost across inference and downstream systems.
• Implement observability with logging, tracing, and debugging of model outputs.

Kenntnisse

High-throughput systems

Low-latency services

Observability

AI inference patterns

System design

Tools

Python

NodeJs

Pytorch

OpenAI / Anthropic / open-source LLMs

SQL & noSQL

Docker

Jobbeschreibung

ActAI is building reliable AI-powered workflows and APIs that scale. We seek a Backend Engineer, AI who owns inference and orchestration between models and users, delivering fast, stable, observable APIs used across clients.

You will collaborate with ML and product teams to translate model capabilities into production-grade systems, focusing on latency, reliability and cost, with production-grade tooling and observability.