Senior AI & LLM Engineer: RAG, Agents & Workflows

Helius Technologies; Singapore; On-site; SGD 70,000 - 130,000; Full time

Job summary

Helius Technologies in Singapore seeks an experienced AI / LLM Engineer to design and develop enterprise AI applications involving Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI agents and intelligent workflow automation.

The role requires strong Python and AI application development experience and the ability to independently deliver AI solutions from design through deployment and continuous improvement.

Qualifications

• Bachelor's degree or above in Computer Science, AI, Machine Learning, NLP, Data Science, Engineering or related discipline.
• At least 2 years of relevant experience in LLM applications, RAG, information retrieval, NLP, AI agents or AI application development.
• Strong hands-on Python programming experience.
• Hands-on experience with LLMs, embeddings, vector databases, semantic search or retrieval systems.
• Practical experience designing or developing RAG architectures.
• Good understanding of prompt engineering, retrieval strategies, evaluation and hallucination mitigation.
• Experience developing AI agents, tool/function calling, agent workflows or backend/API integrations.
• Experience integrating applications with APIs, databases or enterprise systems.
• Ability to independently deliver end-to-end AI/LLM projects.
• Familiarity with Git, automated testing, CI/CD and containerised deployment.
• Strong communication and stakeholder-management skills.

Responsibilities

• Design and develop LLM applications, RAG systems, AI assistants and agentic AI solutions.
• Build AI agents capable of retrieving information, using tools/APIs, executing workflows and interacting with users.
• Develop document ingestion, chunking, embedding, retrieval, prompting, memory and agent-orchestration capabilities.
• Integrate AI applications with enterprise systems, databases, APIs, document repositories and third-party services.
• Implement and optimise semantic search, vector retrieval, reranking and retrieval strategies.
• Work with LLM APIs, open-source models, vector databases and appropriate AI/agent frameworks.
• Develop evaluation approaches for retrieval quality, response accuracy, faithfulness, hallucination, latency and task completion.
• Implement secure enterprise AI patterns including access controls, permission-aware retrieval, guardrails, monitoring and failure handling.
• Independently deliver AI projects across requirements, architecture, development, testing, deployment and optimisation.
• Deploy and maintain AI applications using modern software-engineering and DevOps practices.
• Collaborate with product, software, cloud, data, security, IT and business teams.
• Monitor production performance and continuously improve AI application quality and usability.

Skills

Python programming

LLMs

embeddings

vector databases

semantic search

retrieval systems

RAG architectures

prompt engineering

AI agents

tool calling

API integrations

CI/CD

Git

containerised deployment

Education

Bachelor's degree in Computer Science / AI / ML / NLP / Data Science / Engineering

Job description

Helius Technologies in Singapore seeks an experienced AI / LLM Engineer to design and develop enterprise AI applications involving Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI agents and intelligent workflow automation.

The role requires strong Python and AI application development experience and the ability to independently deliver AI solutions from design through deployment and continuous improvement.