AI Team Leader - Nguyễn Tuân Hà Nội - HN865

· Lead the design and optimization of RAG (Retrieval-Augmented Generation) pipelines.

· Oversee model training, fine-tuning, and evaluation for LLMs and embeddings.

· Architect AI inference services integrating with LangChain, Qdrant, and Elasticsearch.

· Define standards for model observability, data lineage, and output traceability.

· Collaborate with backend and infra teams for scalable AI service deployment.

· Mentor AI and Data Engineers; review code, models, and architecture proposals.

· Continuously evaluate new AI frameworks (Groq, Anthropic, Hugging Face, Voyage AI).

• Report progress, metrics, and performance to CTO and product stakeholders

Must-have

· 6+ years in AI/ML engineering, including 2+ years of team leadership.

· Expertise in Python, PyTorch, LangChain, and LLM-based architectures.

· Deep understanding of semantic retrieval, embedding models, and vector search.

· Experience with data pipeline orchestration (Airflow, Prefect).

· Familiar with Docker/Kubernetes, AWS, and Azure ML environments.

· Strong leadership and mentoring experience

Nice-to-have

· Hands-on with multi-modal AI (text + image).

· Experience implementing LLM observability tools (Langfuse, Weights & Biases).

Knowledge of MLOps and continuous training (CT/CI) pipelines