hirq
← All jobs

Cygnify

Full Stack Developer (AI)

Singapore · On-site · FullTime · Cygnify

Apply well, not just fast

Create a free account and upload your resume to get a match score, keyword gaps, a tailored resume, a cover letter and interview prep for this job.

About the role

LLMsPythonNext.jsNode.jsDockerKubernetesSystem DesignObservabilityMachine LearningPyTorchRAG
Full Stack Engineer – AI Role We are looking for a Full Stack Engineer - AI Systems to build the product layer that turns these capabilities into usable, production-grade workflows. This includes designing how agents operate, fail, recover, and deliver consistent value to users. Focus - Build end-to-end product features across frontend, backend, and AI integrations - Design agent workflows that handle planning, tool use, failure, and recovery across multiple steps. - Integrate LLMs, memory, and external tools into systems that behave reliably under real-world conditions - Design real-time AI interactions with streaming, partial results, and tight latency constraints - Improve system reliability, observability, and fallback mechanisms - Collaborate closely with ML, backend, and product teams to ship features end-to-end - Continuously iterate based on real usage and failure modes Ideal Experiences - Strong experience in full stack engineering (frontend + backend) - Solid understanding of system design and API architecture - Experience working with LLMs, RAG systems, or AI-powered applications - Ability to handle ambiguity and make pragmatic engineering decisions - Strong ownership - able to take features from idea to production - Comfort working in fast-moving environments with evolving requirements Outcomes - Own and ship AI-native product features that move beyond chat into persistent, goal-driven workflows - Design and deploy agent workflows that reliably complete multi-step tasks across tools and sessions - Reduce latency and improve responsiveness of AI interactions while maintaining output quality - Build robust fallback and recovery mechanisms for LLM and tool failures in production environments - Improve the success rate and reliability of AI-driven workflows through iteration, evaluation, and monitoring - Establish patterns and abstractions for integrating LLMs, memory, and external tools into scalable product systems - Contribute to a product experience where AI feels proactive, consistent, and dependable over time Tech Stack - Next.js - Python - NodeJs - Pytorch - OpenAI / Anthropic / open-source LLMs - SQl & noSQL - Kubernetes - Docker