AI Platform – Solution Architect

We are developing a shared AI platform for the business units of a multi-industry group in Vietnam. The platform runs on Kubernetes with LangGraph, FastAPI, and AWS Bedrock, using LangFuse for observability, and enables business teams to build and operate their own AI agents: attaching tools, loading internal documents, and orchestrating multiple agents that work together.

• Design end-to-end architectures for agentic AI and ML solutions, covering agent orchestration, tool integration, knowledge retrieval, and model serving.
• Assess business requirements and recommend suitable approaches across automation, traditional ML, and AI agents, supported by build-versus-buy and cost/ROI analysis.
• Define architecture standards for core AI platform components, ensuring they are scalable, secure, and reusable across teams.
• Evaluate and fine-tune AI/ML models for accuracy, cost, and performance, choosing appropriate techniques for each use case.
• Establish guardrail and responsible-AI standards covering data privacy, safety, and production risk controls.
• Advise engineering teams on technical design, review proposals, and resolve complex implementation decisions.
• Maintain architecture documentation and present solution recommendations and trade-offs to technical and business stakeholders.
• Explore emerging AI/ML technologies through proof-of-concepts and mentor engineers on engineering and architecture best practices.

• A bachelor’s or master’s degree in Computer Science, Data Science, AI, or a related field.
• 8+ years of experience in software engineering or architecture, including at least 2–3 years designing production AI/ML or agentic AI systems.
• A proven track record of leading end-to-end delivery of at least one enterprise-scale AI solution.
• Experience translating business needs into technical roadmaps and advising non-technical stakeholders.
• Strong knowledge of agent and LLM application design, including orchestration, tool use, memory, and retrieval-augmented generation (RAG).
• Experience with major LLM providers and open-source model ecosystems, along with practical knowledge of AI safety, privacy, and risk controls.
• A solid grounding in machine learning and deep learning, with hands-on experience across training, fine-tuning, evaluation, and deployment.
• Familiarity with MLOps practices, including experiment tracking, model versioning, and production monitoring.
• Experience with distributed systems, microservices, cloud platforms, containers, and CI/CD, plus working knowledge of modern web application architecture.
• A strong coding background in Python and/or Java, enabling you to prototype solutions and review implementations hands-on.
• Working knowledge of data governance and compliance considerations for AI in regulated industries.
• Clear communication of technical trade-offs, strong facilitation and stakeholder management skills, and the ability to build consensus across teams.
• Fluent English for technical documentation and stakeholder presentations.

Experience with agent orchestration frameworks and LLM observability tools; a background in forecasting or recommendation systems; relevant cloud architecture or AI/ML certifications; and technical talks, publications, or open-source contributions.

We value architects who understand the wider impact of technical decisions, validate ideas through hands-on work, and take ownership of outcomes from design through production.