Backend Engineer, AI (Agent Systems)

TL;DR

Backend Engineer, AI (Agent Systems): Building and operating inference and orchestration layers for a proactive AI chat app with an accent on high reliability for long-running workflows, persistent context, and real-world task completion. Focus on designing low-latency APIs, optimizing throughput with caching and batching, and ensuring production stability despite non-deterministic model behavior.

Location: Remote (Singapore)

Company

A1 is building a proactive AI chat app for everyday users to bring intelligence to conversations, errands, organising, and workflows.

What you will do

• Build and operate backend systems serving AI-powered features in production.
• Design inference pipelines, orchestration layers, and service boundaries around models.
• Own production concerns including monitoring, logging, alerting, and incident response.
• Optimize latency and throughput across inference, caching, batching, and streaming.
• Turn model capabilities into fast, stable, observable APIs for mobile and desktop clients.

Requirements

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

Culture & Benefits

• Work in small, world-class, high-talent-density teams.
• Make collective decisions at rapid speed, balancing quality and learning.
• Hands-on environment requiring structure, judgment, and independent execution.

Hiring process

• Applications evaluated by technical team members.
• 3-4 interviews via virtual meetings and/or onsite.
• Prompt decisions with offers for exceptional fits.