Responsibilities:

• Design, develop, and deliver end-to-end product features across frontend, backend, and AI integrations.
• Build AI-native product features that extend beyond conversational interfaces into persistent, goal-driven workflows.
• Design and implement intelligent agent workflows capable of planning, tool utilisation, failure handling, and recovery across multiple steps.
• Integrate Large Language Models (LLMs), memory capabilities, Retrieval-Augmented Generation (RAG), and external tools into reliable production systems.
• Develop real-time AI interactions with streaming responses, partial results, and low-latency performance.
• Improve AI response times while maintaining output quality and reliability.
• Build robust fallback, monitoring, observability, and recovery mechanisms for AI models and external tool failures.
• Continuously improve the reliability and success rate of AI-driven workflows through monitoring, evaluation, and iterative enhancements.
• Develop scalable architecture and reusable patterns for integrating LLMs, memory, and external services into production systems.
• Collaborate closely with Machine Learning, Backend, and Product teams to deliver high-quality product features.
• Continuously enhance product performance based on production usage, user feedback, and real-world system behaviour.
• Contribute to delivering a proactive, dependable, and consistent AI user experience.

Requirements:

• Proven experience in full stack software engineering, covering both frontend and backend development.
• Strong understanding of software architecture, system design, and API development.
• Experience working with Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI agents, or AI-powered applications.
• Ability to make sound engineering decisions in ambiguous and rapidly evolving environments.
• Strong ownership mindset with the ability to take features from concept through to production deployment.
• Comfortable working in a fast-paced environment with evolving business and technical requirements.

Technical Environment

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

To apply, please visit www.gmprecruit.com and search for Job Reference: W34W69RW

To learn more about this opportunity, please contact Yingying at yingying.lai@gmprecruit.com

We regret that only shortlisted candidates will be notified.

GMP Technologies (S) Pte Ltd | EA Licence: 11C3793 | EA Personnel: Lai Yingying | Registration No: R1110239