Artificial Intelligence Engineer

Artificial Intelligence Engineer - Hybrid Hanoi office

• candidates must have LLM and Rag experience

Responsibilities

• Design, build, and operate multi-step agentic pipelines that create virtual delivery capacity, surfacing work for engineers to review, accept, or reject.
• Build and evolve the Company's virtual delivery team of specialised agents—including developer, security review, testing, grooming, and criteria cross-check agents—and expand the catalogue as new automation opportunities emerge.
• Develop AI-powered product features and engineering tooling in Python, working directly with squads to embed AI across the SDLC, from code generation and review through testing, PR triage, releases, and incident management.
• Make principled decisions about when to use deterministic logic versus AI models, documenting rationale and developing evaluation patterns, reference implementations, and guardrails to ensure agentic workflows are reliable and auditable.
• Enable engineering squads to identify, scope, build, and own their own agentic workflows, while evaluating orchestration frameworks and tooling choices that can scale across the wider engineering organisation.
• Own AI efficiency and capability-building across engineering, optimising model usage, cost, caching, and prompts while coaching teams on agentic patterns, evaluation, prompt engineering, and when not to use AI.

Requirements

• Bachelor's or Master's degree in Computer Science, Software Engineering, AI, or a related field.
• 10+ years of software engineering experience, including 2+ years building LLM or AI-powered solutions in production.
• Strong understanding of when to use traditional software engineering versus AI/LLM-based approaches, with the ability to communicate technical decisions clearly.
• Hands-on experience building production-grade AI agents or multi-step AI workflows using LangChain, AutoGen, CrewAI, Claude Agent SDK, or similar frameworks.
• Strong Python development skills.
• Practical experience with prompt engineering, RAG, tool/function calling, structured outputs, vector databases, and embeddings.
• Experience applying AI automation across the SDLC, such as code reviews, test generation, PR triage, and CI/CD.
• Experience evaluating and monitoring AI/agent performance and improving output quality.
• Cloud experience, preferably Azure, with an understanding of AI inference cost, performance, reliability, and scalability.