AI Engineer > 3YOE, Offer Upto 50M

We are looking for an AI Engineer (AI Engineer Conversational AI & Application Development) who is collaborative, well-organized, creative, and ready to pursue new opportunities. Most importantly, this role is for individuals who are passionate about making a difference in healthcare.

We are seeking a talented AI Engineer to design, develop, and deploy conversational agents and advanced AI-powered applications. The ideal candidate will combine strong programming skills with a deep interest in modern AI techniques. This role provides the opportunity to work with the latest multi-agent orchestration frameworks such as LangGraph, AutoGen, CrewAI, and Googles Agent Developer Kit (ADK), while leveraging the scalability of Google Cloud Platform (GCP) services including BigQuery, Cloud Run, Kubernetes (GKE), and IAM.

• Design and build multi-agent conversational systems using LangGraph, AutoGen, CrewAI, ADK, or similar frameworks.
• Collaborate with product managers, designers, and engineers to define user journeys, agent capabilities, and integration points.
• Develop robust and scalable backend services and APIs (Python/Golang/Node.js/Java) to support AI agents and orchestration workflows.
• Apply advanced NLP, Retrieval-Augmented Generation (RAG), and LLM fine-tuning techniques for intent recognition, entity extraction, and dynamic dialogue management.
• Deploy and operate conversational workloads on GCP Cloud Run (serverless) and Kubernetes (GKE), following DevOps best practices and implementing secure access controls with IAM.
• Use BigQuery for large-scale data analytics to train, evaluate, and refine ML models and conversational metrics.
• Design and develop interactive dashboards in Power BI or Tableau to visualize KPIs, model performance, and business insights.
• Integrate conversational agents with enterprise systems (databases, CRMs, ERPs) and third-party APIs.
• Implement observability, evaluation, and monitoring for agent performance (latency, accuracy, hallucination rate) using tools such as Arize Phoenix, Langfuse, and LangSmith.
• Contribute to the full software development lifecycle: requirements, architecture, coding, testing, CI/CD, deployment, and maintenance.
• Troubleshoot and resolve production issues to ensure high availability and optimal performance.
• Document technical designs, decisions, and model specifications for cross-functional reference.

• Bachelors or Masters degree in Computer Science, Software Engineering, Artificial Intelligence, Data Science, or a related field.
• Proficiency in at least one backend language/framework:
• Python (FastAPI, Flask, Django)
• Java (Spring Boot)
• Node.js (Express, NestJS)
• Go (Gin, Fiber)
• Experience building RESTful or GraphQL APIs and designing microservices.
• Solid understanding of ML fundamentals: supervised/unsupervised learning, evaluation metrics, feature engineering.
• Familiarity with modern NLP libraries (spaCy, Haystack, Hugging Face Transformers, LlamaIndex).
• Strong version-control habits (Git, trunk-based development) and CI/CD pipelines.
• Excellent problem-solving, communication, and collaboration skills.
• Passion for continuous learning and adapting to emerging AI technologies.

• Hands-on experience creating and deploying production-grade AI chat agents or virtual assistants.
• Working knowledge of LangGraph, AutoGen, CrewAI, ADK, or comparable agent-orchestration/workflow frameworks.
• Experience with LLMs (Gemini, GPT-4, Claude, Mistral, etc.) and vector databases (Weaviate, Chroma, Pinecone).
• Deep expertise with GCP:
• BigQuery for analytical workloads and feature stores
• Cloud Run (serverless) for scalable, cost-efficient microservices
• Google Kubernetes Engine (GKE) for container orchestration and workload portability
• IAM for secure, least-privilege access control
• Business intelligence skills with Power BI or Tableau.
• Familiarity with other cloud providers (AWS, Azure) and their AI/ML services.
• Understanding of MLOps (model registry, continuous training, drift monitoring) and LLM observability tools such as Arize Phoenix, Langfuse, and LangSmith.
• Database skills in both SQL (PostgreSQL, BigQuery) and NoSQL (Firestore, DynamoDB).
• Contributions to open-source AI/ML projects or technical blogging/presentations.

• Strong English communication is required, along with experience working with cloud (especially Google Cloud).
• This role is on-site in Hanoi; no remote or hybrid options. Candidates must attend offline interviews at VMO.
• Keywords: end-to-end expertise in designing, deploying, and maintaining AI agentic systems at scale, particularly regarding production support, monitoring, and advanced concepts.