Backend Engineer, AI (Agent Systems)

We are looking for a Backend Engineer, AI - Agent Systems to join a newly created AI company building a proactive assistant for everyday tasks, email, and workflows.

The business is backed by a profitable technology group operating across Asia and Europe and has received an initial $100M investment, combining startup speed with strong financial stability.

The product is designed to go beyond simple chat. It uses persistent context, external tools, and multi-step reasoning to complete real tasks with minimal prompting.

You’ll own the backend layer between AI models and users, turning LLM capabilities into fast, reliable, and observable services used by mobile and desktop applications.

Responsibilities

• Build and operate backend services powering AI features in production.
• Design inference pipelines, orchestration layers, and clear service boundaries around AI models.
• Develop reliable APIs connecting AI systems with mobile and desktop clients.
• Optimize latency and throughput across inference, caching, batching, and streaming.
• Implement monitoring, logging, alerting, and incident-response processes.
• Improve system performance and reliability based on real production usage.
• Support long-running agent workflows, persistent context, external tool usage, and multi-step task execution.
• Debug distributed systems and production AI services under heavy load.

Requirements

• Strong backend engineering experience in production environments.
• Experience building high-throughput, low-latency services.
• Strong knowledge of distributed systems, reliability, and production debugging.
• Familiarity with AI inference patterns, including LLMs, embeddings, or multimodal models.
• Ability to independently structure and deliver complex technical work.
• Product-oriented mindset and willingness to ship, observe production behaviour, and iterate quickly.
• Working English and strong communication skills.

Tech stack

• Python
• Node.js
• PyTorch
• OpenAI, Anthropic, and open-source LLMs
• SQL and NoSQL databases
• Kubernetes
• Docker

Recruitment process

• Introductory call with the recruitment agency
• Take-home coding assessment reviewed by the technical team
• HR interview
• Technical interview
• Founder interview

Exceptionally strong candidates may follow a shortened process