Middle/Senior AI Engineer

Top 3 reasons to join us

• Open culture & working environment
• Focus on self-development
• Global Business (Not Only Vietnam Market)

Job description

LLM & Conversational AI:

• End-to-End RAG Architecture: Design, build, and optimize robust RAG pipelines using LangChain to orchestrate data, models, and logic.
• Data Ingestion & Processing: Develop workflows for ingesting and processing unstructured data.
• Embedding & Vector Search: Implement and manage embedding strategies using models from OpenAI and Google (Gemini), leveraging vector stores like Chroma, Redis, Elasticsearch, and PostgreSQL.
• LLM Integration & Orchestration: Integrate and manage multiple LLMs (Vertex AI, Azure OpenAI, OpenRouter,...), optimizing for performance, cost, and capability.
• Evaluation & Alignment: Champion continuous improvement by using LangSmith for observability and Guardrails AI to ensure AI outputs are safe, reliable, and on-brand.
• Deployment: Collaborate with our platform team to containerize (Kubernetes) and deploy AI services on Azure, ensuring scalability and efficiency.

Product Recommendation & Personalization:

• Algorithm Development: Build and optimize recommendation models using techniques like collaborative filtering, content-based filtering, matrix factorization, and explore hybrid approaches.
• Feature Engineering: Engineer and select impactful features from user behavior data (clicks, purchases, browsing patterns) and product catalogs to train personalization models.
• Model Lifecycle Management: Own the end-to-end lifecycle of recommendation models, from data preprocessing and training to offline/online evaluation (A/B testing) and production monitoring.
• System Integration: Work with backend engineering teams to integrate recommendation model outputs into the live e-commerce platform via APIs.

Innovation: Research and apply novel techniques, including leveraging LLMs to enhance recommendations (e.g., for cold-start problems or generating natural language explanations for recommendations).

Your skills and experience

• Experience: 3-5+ years of professional experience in AI/ML, with a proven track record of building and deploying models in production.
• Recommendation Systems Expertise: Solid understanding and hands-on experience with recommendation algorithms (e.g., collaborative filtering, content-based). Experience with ML frameworks like PyTorch, TensorFlow, or Scikit-learn is essential.
• LLM Application Proficiency: Demonstrable experience building LLM-powered applications. Hands-on experience with LangChain is a huge plus.
• RAG & Vector Databases: Strong understanding of the RAG architecture and experience with at least one vector database (e.g., Chroma, Pinecone, Weaviate, pgvector,...).
• Programming: Expert-level proficiency in Python and its data science ecosystem (Pandas, NumPy, Scikit-learn).
• Cloud Platforms: Experience developing and deploying applications on a major cloud platform (Azure is preferred).

Nice to Have

• Experience with LLM observability and evaluation tools like LangSmith.
• Familiarity with containerization (Docker) and orchestration (Kubernetes).
• Experience designing and analyzing A/B tests for recommendation systems.

Why you'll love working here

• Engaging and challenging work environment, focusing on the exciting domain of eCommerce.
• Hybrid working model with flexible hours.
• Employee Stock Ownership Program (ESOP): Enjoy the opportunity to be a company stakeholder through our ESOP, fostering a sense of shared success and ownership.