Middle AI Engineer (Agentic AI / LLM Systems)
About the Opportunity
KUP is partnering with a confidential client — a global defense, aerospace, and technology engineering group operating in 100+ countries, with tens of thousands of employees worldwide — to hire a Middle AI Engineer for their Ho Chi Minh City team. This role focuses on building agentic AI systems that automate enterprise support, knowledge retrieval, and multi-step business workflows. 4 openings available.
Key Responsibilities
1. Agentic Solution Design
- Design goal-driven agents that decompose tasks, select tools, manage state, and recover from failures.
- Implement agent patterns such as planner–executor, coordinator–worker, reflection/self-check, and human-in-the-loop decision gates.
2. Platform Implementation (across one or more of the following)
- Microsoft Copilot Studio — build copilots with plugins, connectors, and enterprise guardrails.
- Google AgentSpace — build agents integrated with ITSM/SIEM/workflow systems; orchestrate multi-step, API-driven actions.
- AWS Bedrock — design secure agentic workflows using Bedrock models and tools.
- Dataiku — operationalize agents within analytics, ML pipelines, and business workflows.
- Hybrid ML + LLM systems — e.g., ML detects anomalies → LLM explains them; ML predicts incidents → LLM drafts remediation; ML scores risk → LLM supports human decision-making.
3. Retrieval and Grounding (RAG)
- Design enterprise RAG pipelines: ingestion, chunking, embeddings, retrieval, reranking, citation.
- Ensure retrieval respects role-based access control and data classification.
4. Evaluation, Observability, and Operations
- Build evaluation frameworks for non-deterministic systems: task success metrics, grounding checks, hallucination detection, regression tests.
- Implement observability for prompts, retrieval, and tool calls.
- Own solutions from POC through MVP and production.
5. Security, Governance, and Responsible AI
- Enforce least-privilege tool access, audit logging, secrets management, prompt-injection defenses, safe action boundaries.
- Design human approval checkpoints for high-risk or irreversible actions.
- Comply with enterprise AI governance and ethics requirements.
Requirements
Must Have
- 3–5+ years of professional software engineering experience.
- Hands-on experience building GenAI/LLM systems beyond basic chatbots (e.g., a hybrid ML + LLM model running in an operational platform).
- Practical experience with at least one of: Dataiku, Google Vertex AI Agent (Gemini Enterprise Agent Platform), Microsoft Copilot Studio, Google AgentSpace, or AWS Bedrock.
- Strong understanding of agentic concepts: tool/function calling, state and memory, planning and execution loops.
- Experience with vector databases and embeddings.
- Fluent English.
- Based in Ho Chi Minh City, available for on-site interviews.
Nice to Have
- Familiarity with UiPath.
- Project management fundamentals.
- Experience integrating AI-powered features with SAP systems (SAP BTP AI Core, OData APIs, BAPIs).
- Familiarity with SAP Joule and the SAP AI/Skills Framework.
Why Join This Opportunity
- Large-scale global engineering group, stable and professional environment.
- Performance bonus and regular salary review.
- Company-provided laptop.
- Meal and transportation allowance.
- Full social insurance.
- Flexible working hours (Mon–Fri); work-from-home depends on project arrangement.
How to Apply
Apply via email: [Confidential Information]
