AI Backend Engineer (Agent Systems)

Stack

Responsibilities

• ▹Build, maintain, and operate backend systems that power AI-enabled features in production
• ▹Design and implement AI inference pipelines, orchestration layers, and service architectures around AI models
• ▹Develop scalable, high-performance APIs that integrate seamlessly with frontend applications and machine learning systems
• ▹Optimize system performance by improving inference latency, throughput, caching, batching, and streaming capabilities
• ▹Own production operations, including monitoring, logging, alerting, and incident response
• ▹Troubleshoot and resolve issues within distributed systems to ensure service reliability and stability
• ▹Continuously improve backend architecture and production systems based on operational insights and real-world usage
• ▹Collaborate with cross-functional teams to deliver reliable, scalable, and high-quality AI-powered solutions

Requirements

• ▹Strong backend engineering experience in production environments
• ▹Proven experience building and operating high-throughput, low-latency backend services
• ▹Experience designing scalable APIs and distributed systems
• ▹Familiarity with AI inference patterns, including Large Language Models (LLMs), embeddings, and multimodal AI systems
• ▹Strong debugging and troubleshooting skills within distributed production environments
• ▹Demonstrated ability to deliver production-ready solutions while iterating based on real-world system performance

Nice to have

• ▹Python
• ▹Node.js
• ▹PyTorch
• ▹OpenAI, Anthropic, or open-source Large Language Models (LLMs)
• ▹SQL and NoSQL databases
• ▹Kubernetes
• ▹Docker

Soft skills

About the company

Our client is a stealth AI startup backed by one of Southeast Asia's leading technology companies, currently building its global founding team. It is developing an AI-native communication platform that simplifies everyday tasks by integrating AI directly into conversations, so users no longer need to switch between multiple applications.