AI/ML Developer (Python, LLM, Redis, LLM)

Job description

We are looking for an AI Agent / Applied LLM Engineer to design and build LLM/VLM-based agent systems that automate or support specific tasks based on structured/unstructured data. This role is not just about building simple chatbots, but developing search, reasoning, and execution-based AI systems connected to documents, databases, APIs, and internal systems.

Job Description

• Data Pipeline & Preprocessing: Collect, refine, and structure data (documents, tables, images, logs, DB, etc.) into AI-ready formats. Build pipelines including document parsing, OCR, chunking, and metadata design.
• RAG System Development: Design and implement RAG systems using Embedding, Vector DB, Hybrid Search, and Re-ranking. 
• AI Agent Design: Develop LLM/VLM-based agents capable of Query Routing, Tool Calling, Workflow Orchestration, Multi-step Reasoning, and Human-in-the-loop interaction. 
• System Integration: Develop AI functions integrated with customer systems (DB, ERP, MES, PLM, Groupware, internal APIs) using backend frameworks like FastAPI. 
• Deployment & Optimization: Deploy and operate models and search systems in On-premise or Cloud environments. Monitor and improve response quality, search performance, latency, cost, and stability

Your skills and experience

Requirements

• 2–5 years of experience in LLM/VLM related projects, service development, or research. 
• Strong proficiency in Python and ability to implement systems/services to solve real-world problems. 
• Hands-on experience with core LLM application elements: RAG, Vector DB, search, and Agent Workflows. 
• Experience handling diverse data sources (documents, images, tables, DB, logs).
• Experience with LLM/VLM APIs (OpenAI, Azure OpenAI, Gemini, Anthropic) or Open Source LLMs. 
• Understanding of Prompt Engineering, Structured Output, and Tool Use/Function Calling. 
• Familiarity with data processing (Pandas, SQL) and unstructured data parsing (PyMuPDF, BeautifulSoup, etc.).
• Experience with Backend development (FastAPI, Flask, or Django) and Docker-based deployment.

Preferred Qualifications

• Experience with frameworks such as LangChain, LangGraph, LlamaIndex, DSPy, or Haystack. 
• Experience in fine-tuning, evaluating, or serving open-source LLMs (vLLM, Ollama, etc.).
• Experience designing performance monitoring and evaluation metrics (RAGAS, DeepEval). 
• Experience building AI services in On-premise, private cloud, or air-gapped environments.
• Experience with MLOps and CI/CD pipelines (GitHub Actions, Jenkins).

Tech Stack

• Language: Python, SQL, Bash. 
• AI/LLM: OpenAI, Azure OpenAI, Gemini, Anthropic, Hugging Face. 
• Framework: LangChain, LangGraph, LlamaIndex, FastAPI, Flask. 
• Vector DB/Search: Milvus, Qdrant, Weaviate, Pinecone, Elasticsearch. 
• Infra/Ops: Docker, Kubernetes, Linux, AWS. 
• Data/Monitoring: Pandas, Redis, MLflow, Langfuse. 

Why you'll love working here

• Receive full benefits for employee according to labor law: annual leave, salary, social insurance
• Opportunities for professional learning and training
• Collaborative and innovative work environment
• Working equipment provided by the company
• Join birthday party, holiday party organized by the company
• Review 1 - 2 times per year