Junior AI Engineer (LLM/ Generative AI)

Y3 Technologies Pte Ltd; Singapore; On-site; SGD 90,000 - 130,000; Full time

Job summary

Y3 Technologies Pte Ltd is seeking an AI/LLM-focused developer to build and refine AI-powered applications, including chatbots and document processing, with strong hands-on experience in UI and backend orchestration. You will work on RAG pipelines, prompt engineering, and fine-tuning open-weight models for logistics contexts.

The role emphasizes integrating AI capabilities into legacy Java APIs, evaluating AI outputs, and collaborating with analysts to translate use cases into production

Qualifications

• 1+ years working or project experience on LLM or AI application development
• UI Engineering: Build dynamic, real-time UI components using React and Next.js to handle AI streaming responses, multi-step agent status indicators, and markdown formatting
• AI Backend Orchestration: Design scalable backend API routes and background queues using Node.js and TypeScript
• Hands-on experience with LLM frameworks: LangChain, LangGraph, LlamaIndex, or equivalent
• Understanding of RAG architecture, vector databases, and embedding models
• Experience consuming LLM APIs (OpenAI, Azure OpenAI, Vercel AI, Anthropic Claude)
• Software engineering fundamentals: version control, testing, code review, documentation
• Java development background— ideal for reskilled internal candidates with logistics context
• Fine-tuning experience with open-weight models (Llama, Mistral, Phi)
• Knowledge of logistics domain: freight documents, customs, route planning
• Experience with agentic AI frameworks (AutoGen, CrewAI, LangGraph)

Responsibilities

• Build, iterate, and maintain LLM-powered applications — including chatbots, document processing pipelines, predictive analytics interfaces, and intelligent search systems
• Design and optimise RAG pipelines: chunking strategies, embedding model selection, retrieval tuning, and context window management
• Develop and refine prompt engineering frameworks — maintaining prompt libraries, evaluating prompt performance, and implementing prompt versioning
• Fine-tune open-weight models on logistics data to improve domain accuracy and reduce inference costs
• Integrate LLM capabilities into legacy Java application APIs — building clean abstraction layers that allow AI features without full system rewrites
• Implement LLM evaluation pipelines using automated scoring (faithfulness, relevance, hallucination rate) and human evaluation frameworks
• Collaborate with Business Analysts to translate new use case specifications into production AI features
• Contribute to internal AI documentation, prompt libraries, and reusable component libraries

Skills

LLM/AI app development

UI engineering (React/Next.js)

Backend orchestration (Node.js/TypeSCT

LLM frameworks (LangChain/LangGraph/LR

RAG architecture

APIs: OpenAI/Azure/Claude

Software engineering fundamentals

Java background

Fine-tuning open-weight models

Logistics domain knowledge

Agentic AI frameworks (AutoGen/CrewAI)

Tools

React

Next.js

Node.js

TypeScript

LangChain

LangGraph

LlamaIndex

Job description

• Build, iterate, andmaintain LLM-powered applications — including chatbots, document processingpipelines, predictive analytics interfaces, and intelligent search systems
• Design and optimise RAG(Retrieval Augmented Generation) pipelines: chunking strategies, embeddingmodel selection, retrieval tuning, and context window management
• Develop and refine promptengineering frameworks — maintaining prompt libraries, evaluating promptperformance, and implementing prompt versioning
• Fine-tune open-weightmodels (Llama, Mistral) on YCH-specific logistics data to improve domainaccuracy and reduce inference costs
• Integrate LLM capabilitiesinto YCH's legacy Java application APIs — building clean abstraction layersthat allow AI features without full system rewrites
• Implement LLM evaluationpipelines using automated scoring (faithfulness, relevance, hallucination rate)and human evaluation frameworks
• Collaborate with BusinessAnalysts to translate new use case specifications into production AI features
• Contribute to internal AIdocumentation, prompt libraries, and reusable component libraries

Job Requirements:

• 1+ years working or projectexperience on LLM or AI application development
• User InterfaceEngineering: Build dynamic, real-time UI components using React and Next.js tohandle AI streaming responses, multi-step agent status indicators, and markdownformatting.
• AI BackendOrchestration: Design scalable backend API routes and background event queuesusing Node.js and TypeScript.
• Hands-on experience withLLM frameworks: LangChain, LangGraph, LlamaIndex, or equivalent
• Understanding of RAGarchitecture, vector databases, and embedding models
• Experience consuming LLMAPIs (OpenAI, Azure OpenAI, Vercel AI, Anthropic Claude)
• Solid software engineeringfundamentals: version control, testing, code review, documentation
• Java development background— ideal for reskilled internal candidates with logistics context
• Fine-tuning experience withopen-weight models (Llama, Mistral, Phi)
• Knowledge of logisticsdomain: freight documents, customs, route planning is favoured.
• Experience with agentic AIframeworks (AutoGen, CrewAI, LangGraph)